Vision-language models (VLMs) often inherit the biases and unsafe associations present within their large-scale training dataset. While recent approaches mitigate unsafe behaviors, their evaluation focuses on how safe the model is on unsafe inputs, ignoring potential shortcomings on safe ones. In this paper, we first revise safety evaluation by introducing SafeGround, a new set of metrics that evaluate safety at different levels of granularity. With this metric, we uncover a surprising issue of training-based methods: they make the model less safe on safe inputs. From this finding, we take a different direction and explore whether it is possible to make a model safer without training, introducing Unsafe Weights Manipulation (UWM). UWM uses a calibration set of safe and unsafe instances to compare activations between safe and unsafe content, identifying the most important parameters for processing the latter. Their values are then manipulated via negation. Experiments show that UWM achieves the best tradeoff between safety and knowledge preservation, consistently improving VLMs on unsafe queries while outperforming even training-based state-of-the-art methods on safe ones.Warning: This paper includes unsafe and harmful content that may be disturbing. Such content has been blurred.

As a widely used operation in image editing workflows, image composition has traditionally been studied with a focus on achieving visual realism and semantic plausibility. However, in practical editing scenarios of the modern content creation landscape, many compositions are not intended to preserve realism. Instead, users of online platforms motivated by gaining community recognition often aim to create content that is more artistic, playful, or socially engaging. Taking inspiration from this observation, we define the expressive composition task, a new formulation of image composition that embraces stylistic diversity and looser placement logic, reflecting how users edit images on real-world creative platforms. To address this underexplored problem, we present StickerNet, a two-stage framework that first determines the composition type, then predicts placement parameters such as opacity, mask, location, and scale accordingly. Unlike prior work that constructs datasets by simulating object placements on real images, we directly build our dataset from 1.8 million editing actions collected on an anonymous online visual creation and editing platform, each reflecting user-community validated placement decisions. This grounding in authentic editing behavior ensures strong alignment between task definition and training supervision. User studies and quantitative evaluations show that StickerNet outperforms common baselines and closely matches human placement behavior, demonstrating the effectiveness of learning from real-world editing patterns despite the inherent ambiguity of the task. This work introduces a new direction in visual understanding that emphasizes expressiveness and user intent over realism.

Test-Time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains. Traditional TTA methods primarily adapt model weights based on target data streams, making model performance sensitive to the amount and order of target data. The recently proposed diffusion-driven TTA methods mitigate this by adapting model inputs instead of weights, where an unconditional diffusion model, trained on the source domain, transforms target-domain data into a synthetic domain that is expected to approximate the source domain. However, in this paper, we reveal that although the synthetic data in diffusion-driven TTA seems indistinguishable from the source data, it is unaligned with, or even markedly different from the latter for deep networks. To address this issue, we propose a Synthetic-Domain Alignment (SDA) framework. Our key insight is to fine-tune the source model with synthetic data to ensure better alignment. Specifically, we first employ a conditional diffusion model to generate labeled samples, creating a synthetic dataset. Subsequently, we use the aforementioned unconditional diffusion model to add noise to and denoise each sample before fine-tuning. This Mix of Diffusion (MoD) process mitigates the potential domain misalignment between the conditional and unconditional models. Extensive experiments across classifiers, segmenters, and multimodal large language models (MLLMs, e.g., LLaVA) demonstrate that SDA achieves superior domain alignment and consistently outperforms existing diffusion-driven TTA methods. Our code is available at https://github.com/SHI-Labs/Diffusion-Driven-Test-Time-Adaptation-Via-Synthetic-Domain-Alignment.

Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, simplifying the process of producing diverse and individual content. Current methods excel in generating short videos (up to 16s), but produce hard-cuts when naively extended to long video synthesis. To overcome these limitations, we present StreamingT2V, an autoregressive method that generates long videos of up to 2 minutes or longer with seamless transitions. The key components are: (i) a short-term memory block called conditional attention module (CAM), which conditions the current generation on the features extracted from the preceding chunk via an attentional mechanism, leading to consistent chunk transitions, (ii) a longterm memory block called appearance preservation module (APM), which extracts high-level scene and object features from the first video chunk to prevent the model from forgetting the initial scene, and (iii) a randomized blending approach that allows for the autoregressive application of a video enhancer on videos of indefinite length, ensuring consistency across chunks. Experiments show that StreamingT2V produces more motion, while competing methods suffer from video stagnation when applied naively in an autoregressive fashion. Thus, we propose with StreamingT2V a high-quality seamless text-to-long video generator, surpassing competitors in both consistency and motion.

Text-to-Image (T2I) generative models have revolutionized content creation but remain highly sensitive to prompt phrasing, often requiring users to repeatedly refine prompts multiple times without clear feedback. While techniques such as automatic prompt engineering, controlled text embeddings, denoising, and multi-turn generation mitigate these issues, they offer limited controllability, or often necessitate additional training, restricting the generalization abilities. Thus, we introduce T2I-Copilot, a training-free multi-agent system that leverages collaboration between (Multimodal) Large Language Models to automate prompt phrasing, model selection, and iterative refinement. This approach significantly simplifies prompt engineering while enhancing generation quality and text-image alignment compared to direct generation. Specifically, T2I-Copilot consists of three agents: (1) Input Interpreter, which parses the input prompt, resolves ambiguities, and generates a standardized report; (2) Generation Engine, which selects the appropriate model from different types of T2I models and organizes visual and textual prompts to initiate generation; and (3) Quality Evaluator, which assesses aesthetic quality and text-image alignment, providing scores and feedback for potential regeneration. T2I-Copilot can operate fully autonomously while also supporting human-in-the-loop intervention for fine-grained control. On GenAI-Bench, using open-source generation models, T2I-Copilot achieves a VQA score comparable to commercial models RecraftV3 and Imagen 3, surpasses FLUX1.1-pro by 6.17% at only 16.59% of its cost, and outperforms FLUX.1-dev and SD 3.5 Large by 9.11% and 6.36%. Code will be released at: https://github.com/SHI-Labs/T2I-Copilot.

Recent works in 3D multimodal learning have made remarkable progress. However, typically 3D multimodal models are only capable of handling point clouds. Compared to the emerging 3D representation technique, 3D Gaussian Splatting (3DGS), the spatially sparse point cloud cannot depict the texture information of 3D objects, resulting in inferior reconstruction capabilities. This limitation constrains the potential of point cloud-based 3D multimodal representation learning. In this paper, we present CLIP-GS, a novel multimodal representation learning framework grounded in 3DGS. We introduce the GS Tokenizer to generate serialized gaussian tokens, which are then processed through transformer layers pre-initialized with weights from point cloud models, resulting in the 3DGS embeddings. CLIP-GS leverages contrastive loss between 3DGS and the visual-text embeddings of CLIP, and we introduce an image voting loss to guide the directionality and convergence of gradient optimization. Furthermore, we develop an efficient way to generate triplets of 3DGS, images, and text, facilitating CLIP-GS in learning unified multimodal representations. Leveraging the well-aligned multimodal representations, CLIP-GS demonstrates versatility and outperforms point cloud-based models on various 3D tasks, including multimodal retrieval, zero-shot, and few-shot classification.

Recent progress in text-guided image inpainting, based on the unprecedented success of text-to-image diffusion models, has led to exceptionally realistic and visually plausible results. However, there is still significant potential for improvement in current text-to-image inpainting models, particularly in better aligning the inpainted area with user prompts. Therefore, we introduce $\textit{HD-Painter}$, a $\textbf{training-free}$ approach that $\textbf{accurately follows prompts}$. To this end, we design the $\textit{Prompt-Aware Introverted Attention (PAIntA)}$ layer enhancing self-attention scores by prompt information resulting in better text aligned generations. To further improve the prompt coherence we introduce the $\textit{Reweighting Attention Score Guidance (RASG)}$ mechanism seamlessly integrating a post-hoc sampling strategy into the general form of DDIM to prevent out-of-distribution latent shifts. Our experiments demonstrate that HD-Painter surpasses existing state-of-the-art approaches quantitatively and qualitatively across multiple metrics and a user study. Code is publicly available at: [https://github.com/Picsart-AI-Research/HD-Painter](https://github.com/Picsart-AI-Research/HD-Painter)

Recent text-to-image customization works have proven successful in generating images of given concepts by fine-tuning diffusion models on a few examples. However, tuning-based methods inherently tend to overfit the concepts, resulting in failure to create the concept under multiple conditions (*e.g.*, headphone is missing when generating "a <sks>`dog wearing a headphone"). Interestingly, we notice that the base model before fine-tuning exhibits the capability to compose the base concept with other elements (*e.g.*, "a dog wearing a headphone"), implying that the compositional ability only disappears after personalization tuning. We observe a semantic shift in the customized concept after fine-tuning, indicating that the personalized concept is not aligned with the original concept, and further show through theoretical analyses that this semantic shift leads to increased difficulty in sampling the joint conditional probability distribution, resulting in the loss of the compositional ability. Inspired by this finding, we present **ClassDiffusion**, a technique that leverages a **semantic preservation loss** to explicitly regulate the concept space when learning a new concept. Although simple, this approach effectively prevents semantic drift during the fine-tuning process of the target concepts. Extensive qualitative and quantitative experiments demonstrate that the use of semantic preservation loss effectively improves the compositional abilities of fine-tuning models. Lastly, we also extend our ClassDiffusion to personalized video generation, demonstrating its flexibility.

The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves performance on resolution-sensitive tasks, such as optical character recognition and document analysis. A number of recent MLLMs achieve this goal using a mixture of vision encoders. Despite their success, there is a lack of systematic comparisons and detailed ablation studies addressing critical aspects, such as expert selection and the integration of multiple vision experts. This study provides an extensive exploration of the design space for MLLMs using a mixture of vision encoders and resolutions. Our findings reveal several underlying principles common to various existing strategies, leading to a streamlined yet effective design approach. We discover that simply concatenating visual tokens from a set of complementary vision encoders is as effective as more complex mixing architectures or strategies. We additionally introduce Pre-Alignment to bridge the gap between vision-focused encoders and language tokens, enhancing model coherence. The resulting family of MLLMs, Eagle, surpasses other leading open-source models on major MLLM benchmarks.

Video generation is experiencing a rapid growth, driven by advances in diffusion models and the development of better and larger datasets. However, producing high-quality videos remains challenging, due to the high dimensional data and the complexity of the task. Recent efforts have primarily focused on enhancing visual quality and addressing temporal inconsistencies, such as flickering. Despite progress in these areas, the generated videos often fall short in terms of motion complexity and physical plausibility, with many outputs either appearing static or exhibiting unrealistic motion. In this work, we propose a framework aimed at improving the realism of motion in generated videos, exploring a complementary direction to much of the existing literature. Specifically, we advocate for the incorporation of a retrieval mechanism during the generation phase. The retrieved videos act as grounding signals, providing the model with demonstrations of how the objects move. Our pipeline is designed to apply to any text-to-video diffusion model, conditioning a pre-trained model on the retrieved samples with minimal fine-tuning. We demonstrate the superiority of our approach through established metrics, recently proposed benchmarks, and qualitative results, and we highlight additional applications of the framework. Code available at: https://github.com/helia95/ragme.

In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and undermine the rich visual perception signals present in the data, which are critical for tasks involving spatial reasoning in the domain of embodied AI and robotics. Is it possible to optimize both at the same time? In this work, we propose VisPer-LM, the first approach that infuses visual perception knowledge from expert vision encoders into the LLM's (of an MLLM) hidden representations. We start by investigating MLLMs trained solely with natural language supervision and identify a positive correlation between the quality of visual representations within these models and their downstream performance. Given this insight, we formulate the objective during the pretraining stage in MLLMs as a coupled optimization of predictive visual embedding and next (text) token prediction. Moreover, through extensive probing, we observe improved visual representation quality due to embedding optimization, underscoring the effectiveness of our probing setup. We demonstrate that our VisPer-LM outperforms the single and multi-encoder baselines, proving our approach's superiority over explicitly feeding the corresponding features to the LLM. In particular, VisPer-LM boosts performance by an average margin of up to 2.5% on various benchmarks, with a notable improvement of 8.7% on the Depth task in CV-Bench.

This work challenges the residual prediction paradigm in visual autoregressive modeling and presents FlexVAR, a new Flexible Visual AutoRegressive image generation paradigm. FlexVAR facilitates autoregressive learning with ground-truth prediction, enabling each step to independently produce plausible images. This simple, intuitive approach swiftly learns visual distributions and makes the generation process more flexible and adaptable. Trained solely on low-resolution images (< 256px), FlexVAR can: (1) Generate images of various resolutions and aspect ratios, even exceeding the resolution of the training images. (2) Support various image-to-image tasks, including image refinement, in/out-painting, and image expansion. (3) Adapt to various autoregressive steps, allowing for faster inference with fewer steps or enhancing image quality with more steps. Our 1.0B model outperforms its VAR counterpart on the ImageNet 256 × 256 benchmark. Moreover, when zero-shot transfer the image generation process with 13 steps, the performance further improves to 2.08 FID, outperforming state-of-the-art autoregressive models AiM/VAR by 0.25/0.28 FID and popular diffusion models LDM/DiT by 1.52/0.19 FID, respectively. When transferring our 1.0B model to the ImageNet 512 × 512 benchmark in a zero-shot manner, FlexVAR achieves competitive results compared to the VAR 2.3B model, which is a fully supervised model trained at 512 × 512 resolution.

Recent progress in Text-to-Image (T2I) generative models has enabled high-quality image generation. As performance and accessibility increase, these models are gaining significant attraction and popularity: ensuring their fairness and safety is a priority to prevent the dissemination and perpetuation of biases. However, existing studies in bias detection focus on closed sets of predefined biases (e.g., gender, ethnicity). In this paper, we propose a general framework to identify, quantify, and explain biases in an open set setting, i.e. without requiring a predefined set. This pipeline leverages a Large Language Model (LLM) to propose biases starting from a set of captions. Next, these captions are used by the target generative model for generating a set of images. Finally, Vision Question Answering (VQA) is leveraged for bias evaluation. We show two variations of this framework: OpenBias and GradBias. OpenBias detects and quantifies biases, while GradBias determines the contribution of individual prompt words on biases. OpenBias effectively detects both well-known and novel biases related to people, objects, and animals and highly aligns with existing closed-set bias detection methods and human judgment. GradBias shows that neutral words can significantly influence biases and it outperforms several baselines, including state-of-the-art foundation models.

Despite the significant advancements achieved in image matting, the existing models heavily depend on manually drawn trimaps to produce accurate results in natural image scenarios. However, the process of obtaining trimaps is time-consuming and lacks user-friendliness and device compatibility. This greatly limits the practical applicability of all trimap-based matting methods. To address this issue, we introduceClick2Trimap, an interactive model that is capable of predicting high-quality trimaps and alpha mattes with minimal user click inputs. By analyzing real users’ behavioral logic and the characteristics of trimaps, we successfully propose a powerful iterative three-class training strategy and a dedicated simulation function, making Click2Trimap exhibit versatility across various scenarios. Compared with all existing trimap-free matting methods, Click2Trimap achieves superior performance in quantitative and qualitative assessments conducted on synthetic and real-world matting datasets. In particular, in a user study, Click2Trimap yields high-quality trimap and matting predictions in just 5 seconds per image on average, demonstrating its substantial practical value for use in real-world applications.

Object inpainting is a task that involves adding objects to real images and seamlessly compositing them. With the recent commercialization of products like Stable Diffusion and Generative Fill, inserting objects into images by using prompts has achieved impressive visual results. In this paper, we propose a prompt suggestion model to simplify the process of prompt input. When the user provides an image and a mask, our model predicts suitable prompts based on the partial contextual information in the masked image, and the shape and location of the mask. Specifically, we introduce a concept-diffusion in the CLIP space that predicts CLIP-text embeddings from a masked image. These diffused embeddings can be directly injected into open-source in-painting models like Stable Diffusion and its variants. Alternatively, they can be decoded into natural language for use in other publicly available applications such as Generative Fill. Our prompt suggestion model demonstrates a balanced accuracy and diversity, showing its capability to be both contextually aware and creatively adaptive.

Text-to-image generative models are becoming increasingly popular and accessible to the general public. As these models see large-scale deployments, it is necessary to deeply investigate their safety and fairness to not disseminate and perpetuate any kind of biases. However, existing works focus on detecting closed sets of biases defined a priori, limiting the studies to well-known concepts. In this paper, we tackle the challenge of open-set bias detection in text-to-image generative models presenting OpenBias, a new pipeline that identifies and quantifies the severity of biases agnostically, without access to any precompiled set. OpenBias has three stages. In the first phase, we leverage a Large Language Model (LLM) to propose biases given a set of captions. Secondly, the target generative model produces images using the same set of captions. Lastly, a Vision Question Answering model recognizes the presence and extent of the previously proposed biases. We study the behavior of Stable Diffusion 1.5, 2, and XL emphasizing new biases, never investigated before. Via quantitative experiments, we demonstrate that OpenBias agrees with current closed-set bias detection methods and human judgement.

Generative image editing has recently witnessed extremely fast-paced growth. Some works use high-level conditioning such as text, while others use low-level conditioning. Nevertheless, most of them lack fine-grained control over the properties of the different objects present in the image, i.e. object-level image editing. In this work, we tackle the task by perceiving the images as an amalgamation of various objects and aim to control the properties of each object in a fine-grained manner. Out of these properties, we identify structure and appearance as the most intuitive to understand and useful for editing purposes. We propose PAIR Diffusion, a generic framework that enables a diffusion model to control the structure and appearance properties of each object in the image. We show that having control over the properties of each object in an image leads to comprehensive editing capabilities. Our framework allows for various object-level editing operations on real images such as reference image-based appearance editing, free-form shape editing, adding objects, and variations. Thanks to our design, we do not require any inversion step. Additionally, we propose multi-modal classifier-free guidance which enables editing images using both reference images and text when using our approach with foundational diffusion models. We validate the above claims by extensively evaluating our framework on both unconditional and foundational diffusion models.

Recently, diffusion models have made remarkable progress in text-to-image (T2I) generation, synthesizing images with highfidelity and diverse contents. Despite this advancement, latent space smoothness within diffusion models remains largely unexplored. Smooth latent spaces en-sure that a perturbation on an input latent corresponds to a steady change in the output image. This property proves beneficial in downstream tasks, including image interpolation, inversion, and editing. In this work, we expose the non-smoothness of diffusion latent spaces by observing noticeable visual fluctuations resulting from minor latent variations. To tackle this issue, we propose Smooth Diffusion, a new category of diffusion models that can be simultaneously high-performing and smooth. Specifically, we introduce Step-wise Variation Regularization to enforce the proportion between the variations of an arbitrary input latent and that of the output image is a constant at any diffusion training step. In addition, we devise an interpolation standard deviation (ISTD) metric to effectively assess the latent space smoothness of a diffusion model. Extensive quantitative and qualitative experiments demonstrate that Smooth Diffusion stands out as a more desirable solution not only in T2I generation but also across various downstream tasks. Smooth Diffusion is implemented as a plug-and-play Smooth-LoRA to work with various community models. Code is available at https://github.com/SHI-Labs/Smooth-Diffusion.

Humans possess the remarkable skill of Visual Perception, the ability to see and understand the seen, helping them make sense of the visual world and, in turn, reason. Multimodal Large Language Models (MLLM) have recently achieved impressive performance on vision-language tasks ranging from visual question-answering and image captioning to visual reasoning and image generation. However, when prompted to identify or count (perceive) the entities in a given image, existing MLLM systems fail. Working towards developing an accurate MLLM system for perception and reasoning, we propose using Versatile vision encoders (VCoder) as perception eyes for Multimodal LLMs. We feed the VCoder with perception modalities such as segmentation or depth maps, improving the MLLM's perception abilities. Secondly, we leverage the images from COCO and outputs from off-the-shelf vision perception models to create our COCO Segmentation Text (COST) dataset for training and evaluating MLLMs on the object perception task. Thirdly, we introduce metrics to assess the object perception abilities in MLLMs on our COST dataset. Lastly, we provide extensive experimental evidence proving the VCoder's improved object-level perception skills over existing Multimodal LLMs, including GPT-4V. We open-source our dataset, code, and models to promote research.

We present Zero-Painter, a novel training-free framework for layout-conditional text-to-image synthesis that facilitates the creation of detailed and controlled imagery from textual prompts. Our method utilizes object masks and individual descriptions, coupled with a global text prompt, to generate images with high fidelity. Zero-Painter employs a two-stage process involving our novel Prompt-Adjusted Cross-Attention (PACA) and Region-Grouped Cross-Attention (ReGCA) blocks, ensuring precise alignment of generated objects with textual prompts and mask shapes. Our extensive experiments demonstrate that Zero-Painter surpasses current state-of-the-art methods in preserving textual details and adhering to mask shapes.

Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches. Yet, one pain point persists: the text prompt engineering, and searching high-quality text prompts for customized results is more art than science. Moreover, as commonly argued: “an image is worth a thousand words” - the attempt to describe a desired image with texts often ends up being ambiguous and cannot comprehensively cover delicate visual details, hence necessitating more additional controls from the visual domain. In this paper, we take a bold step forward: taking “Text” out of a pretrained T2I diffusion model, to reduce the burdensome prompt engineering efforts for users. Our proposed frame-work, Prompt-Free Diffusion, relies on only visual inputs to generate new images: it takes a reference image as “context”, an optional image structural conditioning, and an initial noise, with absolutely no text prompt. The core architecture behind the scene is Semantic Context Encoder (SeeCoder), substituting the commonly used CLIP-based or LLM-based text encoder. The reusability of SeeCoder also makes it a convenient drop-in component: one can also pre-train a SeeCoder in one T2I model and reuse it for another. Through extensive experiments, Prompt-Free Diffusion is experimentally found to (i) outperform prior exemplar-based image synthesis approaches; (ii) perform on par with state-of-the-art T2I models using prompts following the best practice; and (iii) be naturally extensible to other downstream applications such as anime figure generation and virtual try-on, with promising quality. Our code and models will be open-sourced.

Text-guided Image Editing has recently attracted significant attention due to advances in the denoising diffusion models field. Current methods make it possible to execute complex image editing operations with simple text prompts. But despite impressive results, they often fail to restrict the edit area to only the object of interest, specified in the text prompt. To this end, we propose a novel framework we name Grounded-Instruct-Pix2Pix, which is capable of localized instruction-guided image editing in various scenarios including multi-object cases and complex backgrounds. Our experiments on a diverse set of images clearly showcase its advantage over the recent state-of-the-art approaches, especially at restricting the editing effect to the area of interest only. Grounded-Instruct-Pix2Pix implementation will be available at https://github.com/arthur-71/Grounded-Instruct-Pix2Pix.

Social reward as a form of community recognition provides a strong source of motivation for users of online platforms to actively engage and contribute with content to accumulate peers approval. In the realm of text-conditioned image synthesis, the recent surge in progress has ushered in a collaborative era where users and AI systems coalesce to refine visual creations. This co-creative pro- cess in the landscape of online social networks empowers users to craft original visual artworks seeking for community validation. Nevertheless, assessing these models in the context of collective community preference introduces distinct chal- lenges. Existing evaluation methods predominantly center on limited size user studies guided by image quality and alignment with prompts. This work pio- neers a paradigm shift, unveiling Social Reward - an innovative reward modeling framework that leverages implicit feedback from social network users engaged in creative editing of generated images. We embark on an extensive journey of dataset curation and refinement, drawing from Picsart: an online visual creation and editing platform, yielding a first million-user-scale dataset of implicit human preferences for user-generated visual art named Picsart Image-Social. Our anal- ysis exposes the shortcomings of current metrics in modeling community creative preference of text-to-image models’ outputs, compelling us to introduce a novel predictive model explicitly tailored to address these limitations. Rigorous quan- titative experiments and user study show that our Social Reward model aligns better with social popularity than existing metrics. Furthermore, we utilize So- cial Reward to fine-tune text-to-image models, yielding images that are more fa- vored by not only Social Reward, but also other established metrics. These find- ings highlight the relevance and effectiveness of Social Reward in assessing com- munity appreciation for AI-generated artworks, establishing a closer alignment with users’ creative goals: creating popular visual art. Codes can be accessed at https://github.com/Picsart-AI-Research/Social-Reward

Recently, diffusion models have made significant strides in synthesizing realistic 2D human images based on provided text prompts. Building upon this, researchers have extended 2D text-to-image diffusion models into the 3D domain for generating human textures (UV Maps). However, some important problems about UV Map Generative models are still not solved, i.e., how to generate personalized texture maps for any given face image, and how to define and evaluate the quality of these generated texture maps. To solve the above problems, we introduce a novel method, UVMap-ID, which is a controllable and personalized UV Map generative model. Unlike traditional large-scale training methods in 2D, we propose to fine-tune a pre-trained text-to-image diffusion model which is integrated with a face fusion module for achieving ID-driven customized generation. To support the finetuning strategy, we introduce a small-scale attribute-balanced training dataset, including high-quality textures with labeled text and Face ID. Additionally, we introduce some metrics to evaluate the multiple aspects of the textures. Finally, both quantitative and qualitative analyses demonstrate the effectiveness of our method in controllable and personalized UV Map generation.

Neighborhood attention reduces the cost of self attention by restricting each token’s attention span to its nearest neighbors. This restriction, parameterized by a window size and dilation factor, draws a spectrum of possible attention patterns between linear projection and self attention. Neighborhood attention, and more generally sliding window attention patterns, have long been bounded by infrastructure, particularly in higher-rank spaces (2-D and 3-D), calling for the development of custom kernels, which have been limited in either functionality, or performance, if not both. In this work, we aim to massively improve upon existing infrastructure by providing two new methods for implementing neighborhood attention. We first show that neighborhood attention can be represented as a batched GEMM problem, similar to standard attention, and implement it for 1-D and 2-D neighborhood attention. These kernels on average provide 895% and 272% improvement in full precision runtime compared to existing naive CUDA kernels for 1-D and 2-D neighborhood attention respectively. We find that aside from being heavily bound by memory bandwidth, certain inherent inefficiencies exist in all unfused implementations of neighborhood attention, which in most cases undo their theoretical efficiency gain. Motivated by the progress made into fused dot-product attention kernels, we developed fused neighborhood attention; an adaptation of fused dot-product attention kernels that allow fine-grained control over attention across different spatial axes. Known for reducing the quadratic time complexity of self attention to a linear complexity, neighborhood attention can now enjoy a reduced and constant memory footprint, and record-breaking half precision runtime. We observe that our fused implementation successfully circumvents some of the unavoidable inefficiencies in unfused implementations. While our unfused GEMM-based kernels only improve half precision performance compared to naive kernels by an average of 548% and 193% in 1-D and 2-D problems respectively, our fused kernels improve naive kernels by an average of 1759% and 958% in 1-D and 2-D problems respectively. These improvements translate into up to 104% improvement in inference and 39% improvement in training existing models based on neighborhood attention, and additionally extend its applicability to image and video perception, as well as other modalities. Our work is open-sourced at https://github.com/SHI-Labs/NATTEN/.

Recent advancements in Multimodal Large Language Models (LLMs) have focused primarily on scaling by increasing text-image pair data and enhancing LLMs to improve performance on multimodal tasks. However, these scaling approaches are computationally expensive and overlook the significance of efficiently improving model capabilities from the vision side. Inspired by the successful applications of Mixture-of-Experts (MoE) in LLMs, which improves model scalability during training while keeping inference costs similar to those of smaller models, we propose CuMo, which incorporates Co-upcycled Top-K sparsely-gated Mixture-of-experts blocks into both the vision encoder and the MLP connector, thereby enhancing the multimodal LLMs with neglectable additional activated parameters during inference. CuMo first pre-trains the MLP blocks and then initializes each expert in the MoE block from the pre-trained MLP block during the visual instruction tuning stage, with auxiliary losses to ensure a balanced loading of experts. CuMo outperforms state-of-the-art multimodal LLMs across various VQA and visual-instruction-following benchmarks within each model size group, all while training exclusively on open-sourced datasets.

Few-shot fine-tuning of text-to-image (T2I) generation models enables people to create unique images in their own style using natural languages without requiring extensive prompt engineering. However, fine-tuning with only a handful, as little as one, of image-text paired data prevents fine-grained control of style attributes at generation. In this paper, we present FineStyle, a few-shot fine-tuning method that allows enhanced controllability for style personalized text-to-image generation. To overcome the lack of training data for fine-tuning, we propose a novel concept-oriented data scaling that amplifies the number of image-text pair, each of which focuses on different concepts (e.g., objects) in the style reference image. We also identify the benefit of parameter-efficient adapter tuning of key and value kernels of cross-attention layers. Extensive experiments show the effectiveness of FineStyle at following fine-grained text prompts and delivering visual quality faithful to the specified style, measured by CLIP scores and human raters.

Video matting aims to predict the alpha mattes for each frame from a given input video sequence. Recent solutions to video matting have been dominated by deep convolutional neural networks (CNN) for the past few years, which have become the de-facto standard for academia and industry. However, they have the inbuilt inductive bias of locality and do not capture the global characteristics of an image due to the CNN-based architectures. They also need long-range temporal modeling considering computational costs when dealing with feature maps of multiple frames. In this paper, we propose VMFormer: a transformer-based end-to-end method for video matting. It makes predictions on alpha mattes of each frame from learnable queries given a video input sequence. Specifically, it leverages self-attention layers to build global integration of feature sequences with short-range temporal modeling on successive frames. We further apply queries to learn global representations through cross-attention in the transformer decoder with long-range temporal modeling upon all queries. In the prediction stage, both queries and corresponding feature maps are used to make the final prediction of alpha mattes. Experiments show that VMFormer outperforms previous CNN-based video matting methods on synthetic benchmarks with different input resolutions, as an end-to-end video matting solution built upon a full vision transformer with predictions on the learnable queries. The project is open-sourced at https://chrisjuniorli.github.io/project/VMFormer.

Conventional video matting outputs one alpha matte for all instances appearing in a video frame so that individual instances are not distinguished. While video instance segmentation provides time-consistent instance masks, results are unsatisfactory for matting applications, especially due to applied binarization. To remedy this deficiency, we propose Video Instance Matting (VIM), that is, estimating alpha mattes of each instance at each frame of a video sequence. To tackle this challenging problem, we present MSG-VIM, a Mask Sequence Guided Video Instance Matting neural network, as a novel baseline model for VIM. MSG-VIM leverages a mixture of mask augmentations to make predictions robust to inaccurate and inconsistent mask guidance. It incorporates temporal mask and temporal feature guidance to improve the temporal consistency of alpha matte predictions. Furthermore, we build a new benchmark for VIM, called VIM50, which comprises 50 video clips with multiple human instances as foreground objects. To evaluate performances on the VIM task, we introduce a suitable metric called Video Instance-aware Matting Quality (VIMQ). Our proposed model MSG-VIM sets a strong baseline on the VIM50 benchmark and outperforms existing methods by a large margin. The project is opensourced at https://github.com/SHI-Labs/VIM.

Whole-body biometric recognition is an important area of research due to its vast applications in law enforcement, border security, and surveillance. This paper presents the end-to-end design, development and evaluation of FarSight, an innovative software system designed for whole-body (fusion of face, gait and body shape) biometric recognition. FarSight accepts videos from elevated platforms and drones as input and outputs a candidate list of identities from a gallery. The system is designed to address several challenges, including (i) low-quality imagery, (ii) large yaw and pitch angles, (iii) robust feature extraction to accommodate large intra-person variabilities and large inter-person similarities, and (iv) the large domain gap between training and test sets. FarSight combines the physics of imaging and deep learning models to enhance image restoration and biometric feature encoding. We test FarSight’s effectiveness using the newly acquired IARPA Biometric Recognition and Identification at Altitude and Range (BRIAR) dataset. Notably, FarSight demonstrated a substantial performance increase on the BRIAR dataset, with gains of +11.82% Rank-20 identification and +11.30% TAR@1% FAR.

Interactive segmentation is the task of segmenting objects or regions of interest from images based on user annotations. While most current methods perform effectively on images from the same distribution as the training dataset, they suffer to generalize on unseen domains. To address this issue some approaches incorporate test-time adaptation techniques which, on the other hand, may lead to catastrophic forgetting (i.e. degrading the performance on the previously seen domains) when applied on datasets from various domains sequentially. In this paper, we propose a novel domain adaptation approach leveraging a teacher-student learning framework to tackle the catastrophic forgetting issue. Continuously updating the student and teacher models based on user clicks results in improved segmentation accuracy on unseen domains, while preserving comparable performance on previous domains. Our approach is evaluated on a sequence of datasets from unseen domains (i.e. medical, aerial images, etc.), and, after adaptation, on the source domain demonstrating a significant decline of catastrophic forgetting (e.g. from 55% to 4% on Berkeley dataset).

We present SPSRC, a novel, simple and effective framework to extract enhanced Structured Pruning Saliency scores by Reorganizing Convolution. We observe that performance of pruning methods have gradually plateaued recently and propose to make better use of the learned convolutional kernel weights simply after a few steps of transformations. We firstly re-organize the convolutional operations between layers as matrix multiplications and then use the singular values and the matrix norms of the transformed matrices as saliency scores to decide what channels to prune or keep. We show both analytically and empirically that the long-standing kernel-norm-based channel importance measurement, like L1 magnitude, is not precise enough possessing a very obvious weakness of lacking spatial saliency but can be improved with SPSRC. We conduct extensive experiments across different settings and configurations and compare with the counterparts without our SPSRC along with other popular methods, observing obvious improvements. Our code is available at: https://github.com/AlexSunNik/SPSRC/tree/main.

This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation. NAS has been explosively studied to automate the discovery of top-performer neural networks, but suffers from heavy resource consumption and often incurs search bias due to truncated training or approximations. Recent NAS works Mellor et al. 2021, Chen et al. 2021, Abdelfattah et al. 2021 start to explore indicators that can predict a network's performance without training. However, they either leveraged limited properties of deep networks, or the benefits of their training-free indicators were not applied to more extensive search methods. By rigorous correlation analysis, we present a unified framework to understand and accelerate NAS, by disentangling “TEG” characteristics of searched networks –Trainability,Expressivity,Generalization– all assessed in a training-free manner. The TEG indicators could be scaled up and integrated with various NAS search methods, including both supernet and single-path NAS approaches. Extensive studies validate the effective and efficient guidance from our TEG-NAS framework, leading to both improved search accuracy and over 56% reduction in search time cost. Moreover, we visualize search trajectories on three landscapes of “TEG” characteristics, observing that a good local minimum is easier to find on NAS-Bench-201 given its simple topology, whereas balancing “TEG” characteristics is much harder on the DARTS space due to its complex landscape geometry.

The existing image-to-video translation methods generally follow a frame-by-frame generative paradigm, while extracting the temporal information from a reference video or an audio stream. Inspired by the recent success in text-guided image generation, we explore a more challenging but promising task, Text-guided Image-to-Video (TI2V) translation. Given an image and a brief text description as input, TI2V aims to generate a facial expression video following the image and text. To this end, we first propose an automatic video captioning pipeline to generate dense textual descriptions for facial video datasets, using both expression labels and action units. These dense textual descriptions provide precise semantic guidance for TI2V learning. Then we design and train an efficient framework, FaceCLIP, on these datasets to deal with the TI2V translation task. FaceCLIP adopts a video autoencoder to model the temporal information of training videos, and a pretrained CLIP model to embed the video frames and the text description. We design a reconstruction loss and an embedding alignment loss to train the autoencoder to obtain the text-guided video generative ability. Recognizing that expressions are closely tied to facial landmark motions, the reconstruction loss is applied to facial landmarks rather than each video frame, significantly enhancing training efficiency. We compare FaceCLIP with several potential baseline methods, and extensively evaluate the performance using multiple metrics. Both qualitative and quantitative results validate the superiority of FaceCLIP in terms of both visual quality and expression-text consistency. Moreover, the unique ability of FaceCLIP to generate videos based on abstract texts demonstrates its stronger generalization capability.

Early-exiting dynamic neural networks (EDNN), as one type of dynamic neural networks, has been widely studied recently. A typical EDNN has multiple prediction heads at different layers of the network backbone. During inference, the model will exit at either the last prediction head or an intermediate prediction head where the prediction confidence is higher than a predefined threshold. To optimize the model, these prediction heads together with the network backbone are trained on every batch of training data. This brings a train-test mismatch problem that all the prediction heads are optimized on all types of data in training phase while the deeper heads will only see difficult inputs in testing phase. Treating training and testing inputs differently at the two phases will cause the mismatch between training and testing data distributions. To mitigate this problem, we formulate an EDNN as an additive model inspired by gradient boosting, and propose multiple training techniques to optimize the model effectively. We name our method BoostNet. Our experiments show it achieves the state-of-the-art performance on CIFAR100 and ImageNet datasets in both anytime and budgeted-batch prediction modes. Our code is released at https://github.com/SHI-Labs/Boosted-Dynamic-Networks.

We present Neighborhood Attention (NA), the first efficient and scalable sliding window attention mechanism for vision. NA is a pixel-wise operation, localizing self attention (SA) to the nearest neighboring pixels, and therefore enjoys a linear time and space complexity compared to the quadratic complexity of SA. The sliding window pattern allows NA's receptive field to grow without needing extra pixel shifts, and preserves translational equivariance, unlike Swin Transformer's Window Self Attention (WSA). We develop NATTEN (Neighborhood Attention Extension), a Python package with efficient C++ and CUDA kernels, which allows NA to run up to 40% faster than Swin's WSA while using up to 25% less memory. We further present Neighborhood Attention Transformer (NAT), a new hierarchical transformer design based on NA that boosts image classification and downstream vision performance. Experimental results on NAT are competitive; NAT-Tiny reaches 83.2% top-1 accuracy on ImageNet, 51.4% mAP on MSCOCO and 48.4% mIoU on ADE20K, which is 1.9% ImageNet accuracy, 1.0% COCO mAP, and 2.6% ADE20K mIoU improvement over a Swin model with similar size. To support more research based on sliding window attention, we open source our project and release our checkpoints.

We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for the challenging graph-constrained house generation task. The proposed graph-Transformer-based generator includes a novel graph Transformer encoder that combines graph convolutions and self-attentions in a Transformer to model both local and global interactions across connected and non-connected graph nodes. Specifically, the proposed connected node attention (CNA) and non-connected node attention (NNA) aim to capture the global relations across connected nodes and non-connected nodes in the input graph, respectively. The proposed graph modeling block (GMB) aims to exploit local vertex interactions based on a house layout topology. More-over, we propose a new node classification-based discriminator to preserve the high-level semantic and discriminative node features for different house components. Finally, we propose a novel graph-based cycle-consistency loss that aims at maintaining the relative spatial relationships between ground truth and predicted graphs. Experiments on two challenging graph-constrained house generation tasks (i.e., house layout and roof generation) with two public datasets demonstrate the effectiveness of GTGAN in terms of objective quantitative scores and subjective visual realism. New state-of-the-art results are established by large margins on both tasks.

Wires and powerlines are common visual distractions that often undermine the aesthetics of photographs. The manual process of precisely segmenting and removing them is extremely tedious and may take up hours, especially on high-resolution photos where wires may span the entire space. In this paper, we present an automatic wire clean-up system that eases the process of wire segmentation and removal/inpainting to within a few seconds. We observe several unique challenges: wires are thin, lengthy, and sparse. These are rare properties of subjects that common segmentation tasks cannot handle, especially in high-resolution images. We thus propose a two-stage method that leverages both global and local contexts to accurately segment wires in high-resolution images efficiently, and a tile-based inpainting strategy to remove the wires given our predicted segmentation masks. We also introduce the first wire segmentation benchmark dataset, WireSegHR. Finally, we demonstrate quantitatively and qualitatively that our wire clean-up system enables fully automated wire removal with great generalization to various wire appearances.

Recently, CLIP-guided image synthesis has shown appealing performance on adapting a pre-trained source-domain generator to an unseen target domain. It does not require any target-domain samples but only the textual domain labels. The training is highly efficient, e.g., a few minutes. However, existing methods still have some limitations in the quality of generated images and may suffer from the mode collapse issue. A key reason is that a fixed adaptation direction is applied for all cross-domain image pairs, which leads to identical supervision signals. To address this issue, we propose an Image-specific Prompt Learning (IPL) method, which learns specific prompt vectors for each source-domain image. This produces a more precise adaptation direction for every cross-domain image pair, endowing the target-domain generator with greatly enhanced flexibility. Qualitative and quantitative evaluations on various domains demonstrate that IPL effectively improves the quality and diversity of synthesized images and alleviates the mode collapse. Moreover, IPL is independent of the structure of the generative model, such as generative adversarial networks or diffusion models. Code is available at https://github.com/Picsart-AI-Research/IPL-Zero-Shot-Generative-Model-Adaptation.

Universal Image Segmentation is not a new concept. Past attempts to unify image segmentation include scene parsing, panoptic segmentation, and, more recently, new panoptic architectures. However, such panoptic architectures do not truly unify image segmentation because they need to be trained individually on the semantic, instance, or panoptic segmentation to achieve the best performance. Ideally, a truly universal framework should be trained only once and achieve SOTA performance across all three image segmentation tasks. To that end, we propose OneFormer, a universal image segmentation framework that unifies segmentation with a multi-task train-once design. We first propose a task-conditioned joint training strategy that enables training on ground truths of each domain (semantic, instance, and panoptic segmentation) within a single multi-task training process. Secondly, we introduce a task token to condition our model on the task at hand, making our model task-dynamic to support multi-task training and inference. Thirdly, we propose using a query-text contrastive loss during training to establish better intertask and inter-class distinctions. Notably, our single OneFormer model outperforms specialized Mask2Former models across all three segmentation tasks on ADE20k, Cityscapes, and COCO, despite the latter being trained on each task individually. We believe OneFormer is a significant step towards making image segmentation more universal and accessible.

Diffusion models have demonstrated impressive capability of text-conditioned image synthesis, and broader application horizons are emerging by personalizing those pretrained diffusion models toward generating some specialized target object or style. In this paper, we aim to learn an unseen style by simply fine-tuning a pre-trained diffusion model with a handful of images (e.g., less than 10), so that the fine-tuned model can generate high-quality images of arbitrary objects in this style. Such extremely lowshot fine-tuning is accomplished by a novel toolkit of finetuning techniques, including text-to-image customized data augmentations, a content loss to facilitate content-style disentanglement, and sparse updating that focuses on only a few time steps. Our framework, dubbed Specialist Diffusion, is plug-and-play to existing diffusion model backbones and other personalization techniques. We demonstrate it to outperform the latest few-shot personalization alternatives of diffusion models such as Textual Inversion [7] and DreamBooth [24], in terms of learning highly sophisticated styles with ultra-sample-efficient tuning. We further show that Specialist Diffusion can be integrated on top of textual inversion to boost performance further, even on highly unusual styles. Our codes are available at: https://github.com/Picsart-AI-Research/Specialist-Diffusion.

Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets. In this paper, we introduce a new task, zero-shot text-to-video generation, and propose a low-cost approach (without any training or optimization) by leveraging the power of existing text-to-image synthesis methods (e.g. Stable Diffusion), making them suitable for the video domain. Our key modifications include (i) enriching the latent codes of the generated frames with motion dynamics to keep the global scene and the background time consistent; and (ii) reprogramming frame-level self-attention using a new cross-frame attention of each frame on the first frame, to preserve the context, appearance, and identity of the foreground object. Experiments show that this leads to low overhead, yet high-quality and remarkably consistent video generation. Moreover, our approach is not limited to text-to-video synthesis but is also applicable to other tasks such as conditional and content-specialized video generation, and Video Instruct-Pix2Pix, i.e., instruction-guided video editing. As experiments show, our method performs comparably or sometimes better than recent approaches, despite not being trained on additional video data. Our code is publicly available at: https://github.com/Picsart-AI-Research/Text2Video-Zero.

In recent years, many deep learning based image inpainting methods have been developed by the research community. Some of those methods have shown impressive image completion abilities. Yet, to the best of our knowledge, there is no image inpainting model designed to run on mobile devices. In this paper we present a simple image inpainting baseline, Mobile Inpainting GAN (MI-GAN), which is approximately one order of magnitude computationally cheaper and smaller than existing state-of-the-art inpainting models, and can be efficiently deployed on mobile devices. Excessive quantitative and qualitative evaluations show that MI-GAN performs comparable or, in some cases, better than recent state-of-the-art approaches. Moreover, we perform a user study comparing MI-GAN results with results from several commercial mobile inpainting applications, which clearly shows the advantage of MI-GAN in comparison to existing apps. With the purpose of high quality and efficient inpainting, we utilize an effective combination of adversarial training, model reparametrization, and knowledge distillation. Our models and code are publicly available at https://github.com/Picsart-AI-Research/MI-GAN.

Recent advances in diffusion models have set an impressive milestone in many generation tasks, and trending works such as DALL-E2, Imagen, and Stable Diffusion have attracted great interest. Despite the rapid landscape changes, recent new approaches focus on extensions and performance rather than capacity, thus requiring separate models for separate tasks. In this work, we expand the existing single-flow diffusion pipeline into a multi-task multimodal network, dubbed Versatile Diffusion (VD), that handles multiple flows of text-to-image, image-to-text, and variations in one unified model. The pipeline design of VD instantiates a unified multi-flow diffusion framework, consisting of sharable and swappable layer modules that enable the crossmodal generality beyond images and text. Through extensive experiments, we demonstrate that VD successfully achieves the following: a) VD outperforms the baseline approaches and handles all its base tasks with competitive quality; b) VD enables novel extensions such as disentanglement of style and semantics, dual- and multi-context blending, etc.; c) The success of our multi-flow multimodal framework over images and text may inspire further diffusion-based universal AI research. Our code and models are open-sourced at https://github.com/SHI-Labs/Versatile-Diffusion.

Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify them. To maintain the CLIP's zero-shot transferability, previous practices favour to freeze CLIP during training. However, in the paper, we reveal that CLIP is insensitive to different mask proposals and tends to produce similar predictions for various mask proposals of the same image. This insensitivity results in numerous false positives when classifying mask proposals. This issue mainly relates to the fact that CLIP is trained with image-level supervision. To alleviate this issue, we propose a simple yet effective method, named Mask-aware Fine-tuning (MAFT). Specifically, Image-Proposals CLIP Encoder (IP-CLIP Encoder) is proposed to handle arbitrary numbers of image and mask proposals simultaneously. Then, *mask-aware loss* and *self-distillation loss* are designed to fine-tune IP-CLIP Encoder, ensuring CLIP is responsive to different mask proposals while not sacrificing transferability. In this way, mask-aware representations can be easily learned to make the true positives stand out. Notably, our solution can seamlessly plug into most existing methods without introducing any new parameters during the fine-tuning process. We conduct extensive experiments on the popular zero-shot benchmarks. With MAFT, the performance of the state-of-the-art methods is promoted by a large margin: 50.4\% (+ 8.2\%) on COCO, 81.8\% (+ 3.2\%) on Pascal-VOC, and 8.7\% (+4.3\%) on ADE20K in terms of mIoU for unseen classes. Codes will be provided for reproducibility. Code is available at https://github.com/jiaosiyu1999/MAFT.git .

Deep image inpainting has made impressive progress with recent advances in image generation and processing algorithms. We claim that the performance of inpainting algorithms can be better judged by the generated structures and textures. Structures refer to the generated object boundary or novel geometric structures within the hole, while texture refers to high-frequency details, especially man-made repeating patterns filled inside the structural regions. We believe that better structures are usually obtained from a coarse-to-fine GAN-based generator network while repeating patterns nowadays can be better modeled using state-of-the-art high-frequency fast fourier convolutional layers. In this paper, we propose a novel inpainting network combining the advantages of the two designs. Therefore, our model achieves a remarkable visual quality to match state-of-the-art performance in both structure generation and repeating texture synthesis using a single network. Extensive experiments demonstrate the effectiveness of the method, and our conclusions further highlight the two critical factors of image inpainting quality, structures, and textures, as the future design directions of inpainting networks.

Controllable image synthesis models allow creation of diverse images based on text instructions or guidance from a reference image. Recently, denoising diffusion probabilistic models have been shown to generate more realistic imagery than prior methods, and have been successfully demonstrated in unconditional and class-conditional settings. We investigate fine-grained, continuous control of this model class, and introduce a novel unified framework for semantic diffusion guidance, which allows either language or image guidance, or both. Guidance is injected into a pretrained unconditional diffusion model using the gradient of image-text or image matching scores, without re-training the diffusion model. We explore CLIP-based language guidance as well as both content and style-based image guidance in a unified framework. Our text-guided synthesis approach can be applied to datasets without associated text annotations. We conduct experiments on FFHQ and LSUN datasets, and show results on fine-grained text-guided image synthesis, synthesis of images related to a style or content reference image, and examples with both textual and image guidance.1

Video stabilization is highly desirable when videos undergo severe jittering artifacts. The difficulty of obtaining sufficient training data obstructs the development of video stabilization. In this work, we address this issue by presenting a Sim2RealVS benchmark with more than 1,300 pairs of shaky and stable videos. Our benchmark is curated by an in-game simulator with diverse scenes and various jittering effects. Moreover, we propose a simple yet strong baseline approach, named Motion-Trajectory Smoothing Network (MTSNet), by fully exploiting our Sim2RealVS data. Our MTSNet consists of three main steps: motion estimation, global trajectory smoothing and frame warping. In motion estimation, we design a Motion Correction and Completion (MCC) module to rectify the optical flow with low confidence, such as in textureless regions, thus providing more consistent motion estimation for next steps. Benefiting from our synthetic data, we can explicitly learn a Trajectory Smoothing Transformer (TST) with ground-truth supervision to smooth global trajectories. In training TST, we propose two fully-supervised losses, i.e., a motion magnitude similarity loss and a motion tendency similarity loss. After training, our TST is able to produce smooth motion trajectories for the shaky input videos. Extensive qualitative and quantitative results demonstrate that our MTSNet achieves superior performance on both synthetic and real-world data.

Image completion with large-scale free-form missing regions is one of the most challenging tasks for the computer vision community. While researchers pursue better solutions, drawbacks such as pattern unawareness, blurry textures, and structure distortion remain noticeable, and thus leave space for improvement. To overcome these challenges, we propose a new StyleGAN-based image completion network, Spectral Hint GAN (SH-GAN), inside which a carefully designed spectral processing module, Spectral Hint Unit, is introduced. We also propose two novel 2D spectral processing strategies, Heterogeneous Filtering and Gaussian Split that well-fit modern deep learning models and may further be extended to other tasks. From our inclusive experiments, we demonstrate that our model can reach FID scores of 3.4134 and 7.0277 on the benchmark datasets FFHQ and Places2, and therefore outperforms prior works and reaches a new state-of-the-art. We also prove the effectiveness of our design via ablation studies, from which one may notice that the aforementioned challenges, i.e. pattern unawareness, blurry textures, and structure distortion, can be noticeably resolved. Our code will be open-sourced at: https://github.com/SHI-Labs/SH-GAN.

In the last few years, Neural Painting (NP) techniques became capable of producing extremely realistic artworks. This paper advances the state of the art in this emerging research domain by proposing the first approach for Interactive NP. Considering a setting where a user looks at a scene and tries to reproduce it on a painting, our objective is to develop a computational framework to assist the user’s creativity by suggesting the next strokes to paint, that can be possibly used to complete the artwork. To accomplish such a task, we propose I-Paint, a novel method based on a conditional transformer Variational AutoEncoder (VAE) architecture with a two-stage decoder. To evaluate the proposed approach and stimulate research in this area, we also introduce two novel datasets. Our experiments show that our approach provides good stroke suggestions and compares favorably to the state of the art.

Abstract Self-similarity refers to the image prior widely used in image restoration algorithms that small but similar patterns tend to occur at different locations and scales. However, recent advanced deep convolutional neural network-based methods for image restoration do not take full advantage of self-similarities by relying on self-attention neural modules that only process information at the same scale. To solve this problem, we present a novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid. Inspired by the fact that corruptions, such as noise or compression artifacts, drop drastically at coarser image scales, our attention module is designed to be able to borrow clean signals from their “clean” correspondences at the coarser levels. The proposed pyramid attention module is a generic building block that can be flexibly integrated into various neural architectures. Its effectiveness is validated through extensive experiments on multiple image restoration tasks: image denoising, demosaicing, compression artifact reduction, and super resolution. Without any bells and whistles, our PANet (pyramid attention module with simple network backbones) can produce state-of-the-art results with superior accuracy and visual quality. Our code is available at https://github.com/SHI-Labs/Pyramid-Attention-Networks

Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a criss-cross network (CCNet) for obtaining full-image contextual information in a very effective and efficient way. Concretely, for each pixel, a novel criss-cross attention module harvests the contextual information of all the pixels on its criss-cross path. By taking a further recurrent operation, each pixel can finally capture the full-image dependencies. Besides, a category consistent loss is proposed to enforce the criss-cross attention module to produce more discriminative features. Overall, CCNet is with the following merits: 1) GPU memory friendly. Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11× less GPU memory usage. 2) High computational efficiency. The recurrent criss-cross attention significantly reduces FLOPs by about 85 percent of the non-local block. 3) The state-of-the-art performance. We conduct extensive experiments on semantic segmentation benchmarks including Cityscapes, ADE20K, human parsing benchmark LIP, instance segmentation benchmark COCO, video segmentation benchmark CamVid. In particular, our CCNet achieves the mIoU scores of 81.9, 45.76 and 55.47 percent on the Cityscapes test set, the ADE20K validation set and the LIP validation set respectively, which are the new state-of-the-art results. The source codes are available at https://github.com/speedinghzl/CCNethttps://github.com/speedinghzl/CCNet.

Salient object detection (SOD) aims to identify the most visually distinctive object(s) from each given image. Most recent progresses focus on either adding elaborative connections among different convolution blocks or introducing boundary-aware supervision to help achieve better segmentation, which is actually moving away from the essence of SOD, i.e., distinctiveness/salience. This paper goes back to the roots of SOD and investigates the principles of how to identify distinctive object(s) in a more effective and efficient way. Intuitively, the salience of one object should largely depend on its global context within the input image. Based on this, we devise a clean yet effective architecture for SOD, named Collaborative Content-Dependent Networks (CCD-Net). In detail, we propose a collaborative content-dependent head whose parameters are conditioned on the input image's global context information. Within the content-dependent head, a hand-crafted multi-scale (HMS) module and a self-induced (SI) module are carefully designed to collaboratively generate content-aware convolution kernels for prediction. Benefited from the content-dependent head, CCD-Net is capable of leveraging global context to detect distinctive object(s) while keeping a simple encoder-decoder design. Extensive experimental results demonstrate that our CCD-Net achieves state-of-the-art results on various benchmarks. Our architecture is simple and intuitive compared to previous solutions, resulting in competitive characteristics with respect to model complexity, operating efficiency, and segmentation accuracy.

In blurry images, the degree of image blurs may vary drastically due to different factors, such as varying speeds of shaking cameras and moving objects, as well as defects of the camera lens. However, current end-to-end models failed to explicitly take into account such diversity of blurs. This unawareness compromises the specialization at each blur level, yielding sub-optimal deblurred images as well as redundant post-processing. Therefore, how to specialize one model simultaneously at different blur levels, while still ensuring coverage and generalization, becomes an emerging challenge. In this work, we propose Ada-Deblur, a super-network that can be applied to a "broad spectrum" of blur levels with no re-training on novel blurs. To balance between individual blur level specialization and wide-range blur levels coverage, the key idea is to dynamically adapt the network architectures from a single well-trained super-network structure, targeting flexible image processing with different deblurring capacities at test time. Extensive experiments demonstrate that our work outperforms strong baselines by demonstrating better reconstruction accuracy while incurring minimal computational overhead. Besides, we show that our method is effective for both synthetic and realistic blurs compared to these baselines. The performance gap between our model and the state-of-the-art becomes more prominent when testing with unseen and strong blur levels. Specifically, our model demonstrates surprising deblurring performance on these images with PSNR improvements of around 1 dB. Our code is publicly available at https://github.com/wuqiuche/Ada-Deblur.

Videos typically record the streaming and continuous visual data as discrete consecutive frames. Since the storage cost is expensive for videos of high fidelity, most of them are stored in a relatively low resolution and frame rate. Recent works of Space-Time Video Super-Resolution (STVSR) are developed to incorporate temporal interpolation and spatial super-resolution in a unified framework. However, most of them only support a fixed up-sampling scale, which limits their flexibility and applications. In this work, instead of following the discrete representations, we propose Video Implicit Neural Representation (VideoINR), and we show its applications for STVSR. The learned implicit neural representation can be decoded to videos of arbitrary spatial resolution and frame rate. We show that VideoINR achieves competitive performances with state-of-the-art STVSR methods on common up-sampling scales and significantly outperforms prior works on continuous and out-of-training-distribution scales. Our project page is at here and code is available at https://github.com/Picsart-AI-Research/VideoINR-Continuous-Space-Time-Super-Resolution.

Image rasterization is a mature technique in computer graphics, while image vectorization, the reverse path of rasterization, remains a major challenge. Recent advanced deep learning-based models achieve vectorization and semantic interpolation of vector graphs and demonstrate a better topology of generating new figures. However, deep models cannot be easily generalized to out-of-domain testing data. The generated SVGs also contain complex and redundant shapes that are not quite convenient for further editing. Specifically, the crucial layer-wise topology and fundamental semantics in images are still not well understood and thus not fully explored. In this work, we propose Layer-wise Image Vectorization, namely LIVE, to convert raster images to SVGs and simultaneously maintain its image topology. LIVE can generate compact SVG forms with layer-wise structures that are semantically consistent with human perspective. We progressively add new bezier paths and optimize these paths with the layer-wise framework, newly designed loss functions, and component-wise path initialization technique. Our experiments demonstrate that LIVE presents more plausible vectorized forms than prior works and can be generalized to new images. With the help of this newly learned topology, LIVE initiates human editable SVGs for both designers and other downstream applications. Codes are made available at https://github.com/Picsart-AI-Research/LIVE-Layerwise-Image-Vectorization.

Despite the popularity of Model Compression and Mul-titask Learning, how to effectively compress a multitask model has been less thoroughly analyzed due to the chal-lenging entanglement of tasks in the parameter space. In this paper, we propose DiSparse, a simple, effective, and first-of-its-kind multitask pruning and sparse training scheme. We consider each task independently by disentangling the importance measurement and take the unani-mous decisions among all tasks when performing parame-ter pruning and selection. Our experimental results demon-strate superior performance on various configurations and settings compared to popular sparse training and pruning methods. Besides the effectiveness in compression, DiS-parse also provides a powerful tool to the multitask learning community. Surprisingly, we even observed better per-formance than some dedicated multitask learning methods in several cases despite the high model sparsity enforced by DiSparse. We analyzed the pruning masks generated with DiSparse and observed strikingly similar sparse net-work architecture identified by each task even before the training starts. We also observe the existence of a “water-shed” layer where the task relatedness sharply drops, implying no benefits in continued parameters sharing. Our code and models will be available at: https://github.com/SHI-Labs/DiSparse-Multitask-Model-Compression.

Recent works have shown that the computational efficiency of video recognition can be significantly improved by reducing the spatial redundancy. As a representative work, the adaptive focus method (AdaFocus) has achieved a favorable trade-off between accuracy and inference speed by dynamically identifying and attending to the informative regions in each video frame. However, AdaFocus requires a complicated three-stage training pipeline (involving reinforcement learning), leading to slow convergence and is unfriendly to practitioners. This work reformulates the training of AdaFocus as a simple one-stage algorithm by introducing a differentiable interpolation-based patch selection operation, enabling efficient end-to-end optimization. We further present an improved training scheme to address the issues introduced by the one-stage formulation, including the lack of supervision, input diversity and training stability. Moreover, a conditional-exit technique is proposed to perform temporal adaptive computation on top of AdaFocus without additional training. Extensive experiments on six benchmark datasets (i.e., ActivityNet, FCVID, Mini-Kinetics, Something-Something V1&V2, and Jester) demonstrate that our model significantly outperforms the original AdaFocus and other competitive baselines, while being considerably more simple and efficient to train. Code is available at https://github.com/LeapLabTHU/AdaFocusV2.

Point-based object localization (POL), which pursues high-performance object sensing under low-cost data annotation, has attracted increased attention. However, the point annotation mode inevitably introduces semantic variance for the inconsistency of annotated points. Existing POL methods heavily reply on accurate keypoint annotations which are difficult to define. In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points. To this end, we propose a coarse point refinement (CPR) approach, which to our best knowledge is the first attempt to alleviate semantic variance from the perspective of algorithm. CPR constructs point bags, selects semantic-correlated points, and produces semantic center points through multiple instance learning (MIL). In this way, CPR defines a weakly supervised evolution procedure, which ensures training high-performance object localizer under coarse point supervision. Experimental results on COCO, DOTA and our proposed SeaPerson dataset validate the effectiveness of the CPR approach. The dataset and code will be available at https://github.com/ucas-vg/PointTinyBenchmark/

Object re-identification (Re ID) is a key application of city-scale cameras on the edge. It is challenged by the limited accuracy of vision algorithms and the large video volume. We present Rev, a practical ReID engine that builds upon three new techniques. (1) Rev formulates ReID as a spatiotemporal query. Instead of retrieving all the images of a target object, it looks for locations and times in which the target object appeared. (2) Rev makes robust assessment of the target object occurrences by clustering unreliable object features. Each resultant cluster represents the general impression of a distinct object. (3) Rev samples cameras strategically in order to maximize its spatiotemporal coverage at low compute cost. Through an evaluation on 25 hours of videos from 25 cameras, Rev reached a high accuracy of 0.87 (recall at 5) across 70 queries. It runs at 830 × of video realtime in achieving high accuracy.

Low-light enhancement is an increasingly important function in image editing and visual creation. Most existing enhancing algorithms are trained to enlighten a given image in a globally homogeneous way, and (implicitly) to some predefined extent of brightness. They are neither capable of enhancing only local regions of interest ("where") while keeping the overall visual appearance plausible, nor producing outputs at a range of different illumination levels ("how much"). Those hurdles significantly limit the prospect of flexible, customizable, or even user-interactive low-light enhancement. To address these gaps, we propose Region-Controllable Robust Light Enhancement (ReCoRo), a novel framework that allows users to directly specify "where" and "how much" they want to enhance from an input low-light image; meanwhile, the model will learn to intelligently maintain the overall consistent visual appearance and plausible composition via a discriminator. Moreover, since in practical mobile APPs, such user specifications often come in imprecise forms (e.g., finger-drawn masks), we propose to bake in domain-specific data augmentations into training ReCoRo, so that the learned model can gain resilience to various roughly-supplied user masks. Up to our best knowledge, ReCoRo is the first of its kind that allows the user to localize the enlightenment region as well as to control the light intensity. Extensive experiments clearly demonstrate that ReCoRo outperforms state-of-the-art methods in terms of qualitative results, quantitative metrics, and versatile controllability. Project repository: https://bit.ly/ReCoRo-lowlight.

In this paper, we aim to tackle the challenging few-shot segmentation task from a new perspective. Typical methods follow the paradigm to firstly learn prototypical features from support images and then match query features in pixel-level to obtain segmentation results. However, to obtain satisfactory segments, such a paradigm needs to couple the learning of the matching operations with heavy segmentation modules, limiting the flexibility of design and increasing the learning complexity. To alleviate this issue, we propose Mask Matching Transformer (MM-Former), a new paradigm for the few-shot segmentation task. Specifically, MM-Former first uses a class-agnostic segmenter to decompose the query image into multiple segment proposals. Then, a simple matching mechanism is applied to merge the related segment proposals into the final mask guided by the support images. The advantages of our MM-Former are two-fold. First, the MM-Former follows the paradigm of 'decompose first and then blend', allowing our method to benefit from the advanced potential objects segmenter to produce high-quality mask proposals for query images. Second, the mission of prototypical features is relaxed to learn coefficients to fuse correct ones within a proposal pool, making the MM-Former be well generalized to complex scenarios or cases. We conduct extensive experiments on the popular COCO-$20^i$ and Pascal-$5^i$ benchmarks. Competitive results well demonstrate the effectiveness and the generalization ability of our MM-Former. Code is available at https://github.com/Picsart-AI-Research/Mask-Matching-Transformer.

Efficient video architecture is the key to deploying video recognition systems on devices with limited computing resources. Unfortunately, existing video architectures are often computationally intensive and not suitable for such applications. The recent X3D work presents a new family of efficient video models by expanding a hand-crafted image architecture along multiple axes, such as space, time, width, and depth. Although operating in a conceptually large space, X3D searches one axis at a time, and merely explored a small set of 30 architectures in total, which does not sufficiently explore the space. This paper bypasses existing 2D architectures, and directly searched for 3D architectures in a fine-grained space, where block type, filter number, expansion ratio and attention block are jointly searched. A probabilistic neural architecture search method is adopted to efficiently search in such a large space. Evaluations on Kinetics and Something-Something-V2 benchmarks confirm our AutoX3D models outperform existing ones in accuracy up to 1.3% under similar FLOPs, and reduce the computational cost up to ×1.74 when reaching similar performance.

Aggregating features in terms of different convolutional blocks or contextual embeddings has been proven to be an effective way to strengthen feature representations for semantic segmentation. However, most of the current popular network architectures tend to ignore the misalignment issues during the feature aggregation process caused by step-by-step downsampling operations and indiscriminate contextual information fusion. In this paper, we explore the principles in addressing such feature misalignment issues and inventively propose Feature-Aligned Segmentation Networks (AlignSeg). AlignSeg consists of two primary modules, i.e., the Aligned Feature Aggregation (AlignFA) module and the Aligned Context Modeling (AlignCM) module. First, AlignFA adopts a simple learnable interpolation strategy to learn transformation offsets of pixels, which can effectively relieve the feature misalignment issue caused by multi-resolution feature aggregation. Second, with the contextual embeddings in hand, AlignCM enables each pixel to choose private custom contextual information adaptively, making the contextual embeddings be better aligned. We validate the effectiveness of our AlignSeg network with extensive experiments on Cityscapes and ADE20K, achieving new state-of-the-art mIoU scores of 82.6 and 45.95 percent, respectively. Our source code is available at https://github.com/speedinghzl/AlignSeg.

Video instance segmentation is a complex task in which we need to detect, segment, and track each object for any given video. Previous approaches only utilize single-frame features for the detection, segmentation, and tracking of objects and they suffer in the video scenario due to several distinct challenges such as motion blur and drastic appearance change. To eliminate ambiguities introduced by only using single-frame features, we propose a novel comprehensive feature aggregation approach (CompFeat) to refine features atboth frame-level and object-level with temporal and spatial context information. The aggregation process is carefully designed with a new attention mechanism which significantly increases the discriminative power of the learned features. We further improve the tracking capability of our model through a siamese design by incorporating both feature similarities and spatial similarities. Experiments conducted on the YouTube-VIS dataset validate the effectiveness of proposed CompFeat.

We present any-precision deep neural networks (DNNs), which are trained with a new method that allows the learned DNNs to be flexible in numerical precision during inference. The same model in runtime can be flexibly and directly set to different bit-widths, by truncating the least significant bits, to support dynamic speed and accuracy trade-off. When all layers are set to low-bits, we show that the model achieved accuracy comparable to dedicated models trained at the same precision. This nice property facilitates flexible deployment of deep learning models in real-world applications, where in practice trade-offs between model accuracy and runtime efficiency are often sought. Previous literature presents solutions to train models at each individual fixed efficiency/accuracy trade-off point. But how to produce a model flexible in runtime precision is largely unexplored. When the demand of efficiency/accuracy trade-off varies from time to time or even dynamically changes in runtime, it is infeasible to re-train models accordingly, and the storage budget may forbid keeping multiple models. Our proposed framework achieves this flexibility without performance degradation. More importantly, we demonstrate that this achievement is agnostic to model architectures and applicable to multiple vision tasks. Our code is released at https://github.com/SHI-Labs/Any-Precision-DNNs.

Image matting is a key technique for image and video editing and composition. Conventionally, deep learning approaches take the whole input image and an associated trimap to infer the alpha matte using convolutional neural networks. Such approaches set state-of-the-arts in image matting; however, they may fail in real-world matting applications due to hardware limitations, since real-world input images for matting are mostly of very high resolution. In this paper, we propose HDMatt, a first deep learning based image matting approach for high-resolution inputs. More concretely, HDMatt runs matting in a patch-based crop-and-stitch manner for high-resolution inputs with a novel module design to address the contextual dependency and consistency issues between different patches. Compared with vanilla patch-based inference which computes each patch independently, we explicitly model the cross-patch contextual dependency with a newly-proposed Cross-Patch Contextual module (CPC) guided by the given trimap. Extensive experiments demonstrate the effectiveness of the proposed method and its necessity for high-resolution inputs. Our HDMatt approach also sets new state-of-the-art performance on Adobe Image Matting and AlphaMatting benchmarks and produce impressive visual results on more real-world high-resolution images.

While recent studies on semi-supervised learning have shown remarkable progress in leveraging both labeled and unlabeled data, most of them presume a basic setting of the model is randomly initialized. In this work, we consider semi-supervised learning and transfer learning jointly, leading to a more practical and competitive paradigm that can utilize both powerful pre-trained models from source domain as well as labeled/unlabeled data in the target domain. To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization that consists of two complementary components: Adaptive Knowledge Consistency (AKC) on the examples between the source and target model, and Adaptive Representation Consistency (ARC) on the target model between labeled and unlabeled examples. Examples involved in the consistency regularization are adaptively selected according to their potential contributions to the target task. We conduct extensive experiments on popular benchmarks including CIFAR-10, CUB-200, and MURA, by fine-tuning the ImageNet pre-trained ResNet-50 model. Results show that our proposed adaptive consistency regularization outperforms state-of-the-art semi-supervised learning techniques such as Pseudo Label, Mean Teacher, and FixMatch. Moreover, our algorithm is orthogonal to existing methods and thus able to gain additional improvements on top of MixMatch and FixMatch. Our code is available at https://github.com/Walleclipse/Semi-Supervised-Transfer-Learning-Paddle.

Tracking segmentation masks of multiple instances has been intensively studied, but still faces two fundamental challenges: 1) the requirement of large-scale, frame-wise annotation, and 2) the complexity of two-stage approaches. To resolve these challenges, we introduce a novel semisupervised framework by learning instance tracking networks with only a labeled image dataset and unlabeled video sequences. With an instance contrastive objective, we learn an embedding to discriminate each instance from the others. We show that even when only trained with images, the learned feature representation is robust to instance appearance variations, and is thus able to track objects steadily across frames. We further enhance the tracking capability of the embedding by learning correspondence from unlabeled videos in a self-supervised manner. In addition, we integrate this module into single-stage instance segmentation and pose estimation frameworks, which significantly reduce the computational complexity of tracking compared to two-stage networks. We conduct experiments on the YouTube-VIS and PoseTrack datasets. Without any video annotation efforts, our proposed method can achieve comparable or even better performance than most fullysupervised methods1.

Text segmentation is a prerequisite in many real-world text-related tasks, e.g., text style transfer, and scene text removal. However, facing the lack of high-quality datasets and dedicated investigations, this critical prerequisite has been left as an assumption in many works, and has been largely overlooked by current research. To bridge this gap, we proposed TextSeg, a large-scale fine-annotated text dataset with six types of annotations: word- and character-wise bounding polygons, masks, and transcriptions. We also introduce Text Refinement Network (TexRNet), a novel text segmentation approach that adapts to the unique properties of text, e.g. non-convex boundary, diverse texture, etc., which often impose burdens on traditional segmentation models. In our TexRNet, we propose text-specific network designs to address such challenges, including key features pooling and attention-based similarity checking. We also introduce trimap and discriminator losses that show significant improvement in text segmentation. Extensive experiments are carried out on both our TextSeg dataset and other existing datasets. We demonstrate that TexRNet consistently improves text segmentation performance by nearly 2% compared to other state-of-the-art segmentation methods. Our dataset and code can be found at https://github.com/SHI-Labs/Rethinking-TextSegmentation.

Most existing few-shot classification methods only consider generalization on one dataset (i.e., single-domain), failing to transfer across various seen and unseen domains. In this paper, we consider the more realistic multi-domain few-shot classification problem to investigate the cross-domain generalization. Two challenges exist in this new setting: (1) how to efficiently generate multi-domain feature representation, and (2) how to explore domain correlations for better cross-domain generalization. We propose a parameter-efficient multi-mode modulator to address both challenges. First, the modulator is designed to maintain multiple modulation parameters (one for each domain) in a single network, thus achieving single-network multi-domain representation. Given a particular domain, domain-aware features can be efficiently generated with the well-devised separative selection module and cooperative query module. Second, we further divide the modulation parameters into the domain-specific set and the domain-cooperative set to explore the intra-domain information and inter-domain correlations, respectively. The intra-domain information describes each domain independently to prevent negative interference. The inter-domain correlations guide information sharing among relevant domains to enrich their own representation. Moreover, unseen domains can utilize the correlations to obtain an adaptive combination of seen domains for extrapolation. We demonstrate that the proposed multi-mode modulator achieves state-of-the-art results on the challenging META-DATASET benchmark, especially for unseen test domains.

We study the problem of concept induction in visual reasoning, i.e., identifying concepts and their hierarchical relationships from question-answer pairs associated with images; and achieve an interpretable model via working on the induced symbolic concept space. To this end, we first design a new framework named object-centric compositional attention model (OCCAM) to perform the visual reasoning task with object-level visual features. Then, we come up with a method to induce concepts of objects and relations using clues from the attention patterns between objects’ visual features and question words. Finally, we achieve a higher level of interpretability by imposing OCCAM on the objects represented in the induced symbolic concept space. Experiments on the CLEVR and GQA datasets demonstrate: 1) our OCCAM achieves a new state of the art without human-annotated functional programs; 2) our induced concepts are both accurate and sufficient as OCCAM achieves an on-par performance on objects represented either in visual features or in the induced symbolic concept space.

Discriminative learning based image denoisers have achieved promising performance on synthetic noises such as Additive White Gaussian Noise (AWGN). The synthetic noises adopted in most previous work are pixel-independent, but real noises are mostly spatially/channel-correlated and spatially/channel-variant. This domain gap yields unsatisfied performance on images with real noises if the model is only trained with AWGN. In this paper, we propose a novel approach to boost the performance of a real image denoiser which is trained only with synthetic pixel-independent noise data dominated by AWGN. First, we train a deep model that consists of a noise estimator and a denoiser with mixed AWGN and Random Value Impulse Noise (RVIN). We then investigate Pixel-shuffle Down-sampling (PD) strategy to adapt the trained model to real noises. Extensive experiments demonstrate the effectiveness and generalization of the proposed approach. Notably, our method achieves state-of-the-art performance on real sRGB images in the DND benchmark among models trained with synthetic noises. Codes are available at https://github.com/yzhouas/PD-Denoising-pytorch.

Bottom-up human pose estimation methods have difficulties in predicting the correct pose for small persons due to challenges in scale variation. In this paper, we present HigherHRNet: a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids. Equipped with multi-resolution supervision for training and multi-resolution aggregation for inference, the proposed approach is able to solve the scale variation challenge in bottom-up multi-person pose estimation and localize keypoints more precisely, especially for small person. The feature pyramid in HigherHRNet consists of feature map outputs from HRNet and upsampled higher-resolution outputs through a transposed convolution. HigherHRNet outperforms the previous best bottom-up method by 2.5% AP for medium person on COCO test-dev, showing its effectiveness in handling scale variation. Furthermore, HigherHRNet achieves new state-of-the-art result on COCO test-dev (70.5% AP) without using refinement or other post-processing techniques, surpassing all existing bottom-up methods. HigherHRNet even surpasses all top-down methods on CrowdPose test (67.6% AP), suggesting its robustness in crowded scene.

The success of deep learning in visual recognition tasks has driven advancements in multiple fields of research. Particularly, increasing attention has been drawn towards its application in agriculture. Nevertheless, while visual pattern recognition on farmlands carries enormous economic values, little progress has been made to merge computer vision and crop sciences due to the lack of suitable agricultural image datasets. Meanwhile, problems in agriculture also pose new challenges in computer vision. For example, semantic segmentation of aerial farmland images requires inference over extremely large-size images with extreme annotation sparsity. These challenges are not present in most of the common object datasets, and we show that they are more challenging than many other aerial image datasets. To encourage research in computer vision for agriculture, we present Agriculture-Vision: a large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns. We collected 94,986 high-quality aerial images from 3,432 farmlands across the US, where each image consists of RGB and Near-infrared (NIR) channels with resolution as high as 10 cm per pixel. We annotate nine types of field anomaly patterns that are most important to farmers. As a pilot study of aerial agricultural semantic segmentation, we perform comprehensive experiments using popular semantic segmentation models; we also propose an effective model designed for aerial agricultural pattern recognition. Our experiments demonstrate several challenges Agriculture-Vision poses to both the computer vision and agriculture communities. Future versions of this dataset will include even more aerial images, anomaly patterns and image channels.

Deep convolution-based single image super-resolution (SISR) networks embrace the benefits of learning from large-scale external image resources for local recovery, yet most existing works have ignored the long-range feature-wise similarities in natural images. Some recent works have successfully leveraged this intrinsic feature correlation by exploring non-local attention modules. However, none of the current deep models have studied another inherent property of images: cross-scale feature correlation. In this paper, we propose the first Cross-Scale Non-Local (CS-NL) attention module with integration into a recurrent neural network. By combining the new CS-NL prior with local and in-scale non-local priors in a powerful recurrent fusion cell, we can find more cross-scale feature correlations within a single low-resolution (LR) image. The performance of SISR is significantly improved by exhaustively integrating all possible priors. Extensive experiments demonstrate the effectiveness of the proposed CS-NL module by setting new state-of-the-arts on multiple SISR benchmarks.

We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (real data) in this work. State-of-the-art approaches prove that performing semantic-level alignment is helpful in tackling the domain shift issue. Based on the observation that stuff categories usually share similar appearances across images of different domains while things (i.e. object instances) have much larger differences, we propose to improve the semantic-level alignment with different strategies for stuff regions and for things: 1) for the stuff categories, we generate feature representation for each class and conduct the alignment operation from the target domain to the source domain; 2) for the thing categories, we generate feature representation for each individual instance and encourage the instance in the target domain to align with the most similar one in the source domain. In this way, the individual differences within thing categories will also be considered to alleviate over-alignment. In addition to our proposed method, we further reveal the reason why the current adversarial loss is often unstable in minimizing the distribution discrepancy and show that our method can help ease this issue by minimizing the most similar stuff and instance features between the source and the target domains. We conduct extensive experiments in two unsupervised domain adaptation tasks, i.e. GTA5 → Cityscapes and SYNTHIA → Cityscapes, and achieve the new state-of-the-art segmentation accuracy.

Motion estimation of cardiac MRI videos is crucial for the evaluation of human heart anatomy and function. Recent researches show promising results with deep learning-based methods. In clinical deployment, however, they suffer dramatic performance drops due to mismatched distributions between training and testing datasets, commonly encountered in the clinical environment. On the other hand, it is arguably impossible to collect all representative datasets and to train a universal tracker before deployment. In this context, we proposed a novel fast online adaptive learning (FOAL) framework: an online gradient descent based optimizer that is optimized by a meta-learner. The meta-learner enables the online optimizer to perform a fast and robust adaptation. We evaluated our method through extensive experiments on two public clinical datasets. The results showed the superior performance of FOAL in accuracy compared to the offline-trained tracking method. On average, the FOAL took only 0.4 second per video for online optimization.

Despite the remarkable progress in person re-identification (Re-ID), such approaches still suffer from the failure cases where the discriminative body parts are missing. To mitigate this type of failure, we propose a simple yet effective Horizontal Pyramid Matching (HPM) approach to fully exploit various partial information of a given person, so that correct person candidates can be identified even if some key parts are missing. With HPM, we make the following contributions to produce more robust feature representations for the Re-ID task: 1) we learn to classify using partial feature representations at different horizontal pyramid scales, which successfully enhance the discriminative capabilities of various person parts; 2) we exploit average and max pooling strategies to account for person-specific discriminative information in a global-local manner. To validate the effectiveness of our proposed HPM method, extensive experiments are conducted on three popular datasets including Market-1501, DukeMTMCReID and CUHK03. Respectively, we achieve mAP scores of 83.1%, 74.5% and 59.7% on these challenging benchmarks, which are the new state-of-the-arts.

Semantic scene parsing is suffering from the fact that pixellevel annotations are hard to be collected. To tackle this issue, we propose a Point-based Distance Metric Learning (PDML) in this paper. PDML does not require dense annotated masks and only leverages several labeled points that are much easier to obtain to guide the training process. Concretely, we leverage semantic relationship among the annotated points by encouraging the feature representations of the intra- and intercategory points to keep consistent, i.e. points within the same category should have more similar feature representations compared to those from different categories. We formulate such a characteristic into a simple distance metric loss, which collaborates with the point-wise cross-entropy loss to optimize the deep neural networks. Furthermore, to fully exploit the limited annotations, distance metric learning is conducted across different training images instead of simply adopting an image-dependent manner. We conduct extensive experiments on two challenging scene parsing benchmarks of PASCALContext and ADE 20K to validate the effectiveness of our PDML, and competitive mIoU scores are achieved.

Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural networks is to fine-tune a model pretrained on the source task using data from the target task. In this paper, we propose an adaptive fine-tuning approach, called SpotTune, which finds the optimal fine-tuning strategy per instance for the target data. In SpotTune, given an image from the target task, a policy network is used to make routing decisions on whether to pass the image through the fine-tuned layers or the pre-trained layers. We conduct extensive experiments to demonstrate the effectiveness of the proposed approach. Our method outperforms the traditional fine-tuning approach on 12 out of 14 standard datasets. We also compare SpotTune with other state-of-the-art fine-tuning strategies, showing superior performance. On the Visual Decathlon datasets, our method achieves the highest score across the board without bells and whistles.

It has been shown that jointly reasoning the 2D appearance and 3D information from RGB-D domains is beneficial to indoor scene semantic segmentation. However, most existing approaches require accurate depth map as input to segment the scene which severely limits their applications. In this paper, we propose to jointly infer the semantic and depth information by distilling geometry-aware embedding to eliminate such strong constraint while still exploiting the helpful depth domain information. In addition, we use this learned embedding to improve the quality of semantic segmentation, through a proposed geometry-aware propagation framework followed by several multi-level skip feature fusion blocks. By decoupling the single task prediction network into two joint tasks of semantic segmentation and geometry embedding learning, together with the proposed information propagation and feature fusion architecture, our method is shown to perform favorably against state-of-the-art methods for semantic segmentation on publicly available challenging indoor datasets.

Multi-scale context module and single-stage encoder-decoder structure are commonly employed for semantic segmentation. The multi-scale context module refers to the operations to aggregate feature responses from a large spatial extent, while the single-stage encoder-decoder structure encodes the high-level semantic information in the encoder path and recovers the boundary information in the decoder path. In contrast, multi-stage encoder-decoder networks have been widely used in human pose estimation and show superior performance than their single-stage counterpart. However, few efforts have been attempted to bring this effective design to semantic segmentation. In this work, we propose a Semantic Prediction Guidance (SPG) module which learns to re-weight the local features through the guidance from pixel-wise semantic prediction. We find that by carefully re-weighting features across stages, a two-stage encoder-decoder network coupled with our proposed SPG module can significantly outperform its one-stage counterpart with similar parameters and computations. Finally, we report experimental results on the semantic segmentation benchmark Cityscapes, in which our SPGNet attains 81.1% on the test set using only 'fine' annotations.

Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the similar natural characteristics existing in the samples from the target domain for learning to conduct person re-ID in an unsupervised manner. Concretely, we propose a Self-similarity Grouping (SSG) approach, which exploits the potential similarity (from the global body to local parts) of unlabeled samples to build multiple clusters from different views automatically. These independent clusters are then assigned with labels, which serve as the pseudo identities to supervise the training process. We repeatedly and alternatively conduct such a grouping and training process until the model is stable. Despite the apparent simplify, our SSG outperforms the state-of-the-arts by more than 4.6% (DukeMTMC→Market1501) and 4.4% (Market1501→DukeMTMC) in mAP, respectively. Upon our SSG, we further introduce a clustering-guided semisupervised approach named SSG ++ to conduct the one-shot domain adaption in an open set setting (i.e. the number of independent identities from the target domain is unknown). Without spending much effort on labeling, our SSG ++ can further promote the mAP upon SSG by 10.7% and 6.9%, respectively. Our Code is available at: https://github.com/OasisYang/SSG .

Despite the remarkable progress, weakly supervised segmentation approaches are still inferior to their fully supervised counterparts. We obverse the performance gap mainly comes from their limitation on learning to produce high-quality dense object localization maps from image-level supervision. To mitigate such a gap, we revisit the dilated convolution [1] and reveal how it can be utilized in a novel way to effectively overcome this critical limitation of weakly supervised segmentation approaches. Specifically, we find that varying dilation rates can effectively enlarge the receptive fields of convolutional kernels and more importantly transfer the surrounding discriminative information to non-discriminative object regions, promoting the emergence of these regions in the object localization maps. Then, we design a generic classification network equipped with convolutional blocks of different dilated rates. It can produce dense and reliable object localization maps and effectively benefit both weakly- and semi- supervised semantic segmentation. Despite the apparent simplicity, our proposed approach obtains superior performance over state-of-the-arts. In particular, it achieves 60.8% and 67.6% mIoU scores on Pascal VOC 2012 test set in weakly- (only image-level labels are available) and semi- (1,464 segmentation masks are available) supervised settings, which are the new state-of-the-arts.

The practical application of Computed Tomography (CT) faces the dilemma between higher image resolution and less X-ray exposure for patients, motivating the research on CT super-resolution (SR). In this paper, we apply state-of-the-art SR techniques to reconstruct CT images using two proposed advanced CT SR models based on Convolutional Neural Networks (CNNs) and residual learning: a single-slice CT SR network (S-CTSRN), and a multi-slice CT SR network (M-CTSRN). S-CTSRN improves the high-frequency feature extraction by incorporating the residual learning strategy, while M-CTSRN further utilizes the coherence between neighboring CT slices for better SR reconstruction. We evaluate both models on a large-scale CT dataset1, and obtain competitive results both quantitatively and qualitatively.

We propose Epitomic Image Super-Resolution (ESR) to enhance the current internal SR methods that exploit the self-similarities in the input. Instead of local nearest neighbor patch matching used in most existing internal SR methods, ESR employs epitomic patch matching that features robustness to noise, and both local and non-local patch matching. Extensive objective and subjective evaluation demonstrate the effectiveness and advantage of ESR on various images.