Accurate detection of offensive content on social media demands high-quality labeled data; however, such data is often scarce due to the low prevalence of offensive instances and the high cost of manual annotation. To address this low-resource challenge, we propose a self-training framework that leverages abundant unlabeled data through collaborative pseudo-labeling. Starting with a lightweight classifier trained on limited labeled data, our method iteratively assigns pseudo-labels to unlabeled instances with the support of Multi-Agent Vision-Language Models (MA-VLMs). Unlabeled data on which the classifier and MA-VLMs agree are designated as the Agreed-Unknown set, while conflicting samples form the Disagreed-Unknown set. To enhance label reliability, MA-VLMs simulate dual perspectives, moderator and user, capturing both regulatory and subjective viewpoints. The classifier is optimized using a novel Positive-Negative-Unlabeled (PNU) loss, which jointly exploits labeled, Agreed-Unknown, and Disagreed-Unknown data while mitigating pseudo-label noise. Experiments on benchmark datasets demonstrate that our framework substantially outperforms baselines under limited supervision and approaches the performance of large-scale models.

Live streaming platforms require real-time monitoring and reaction to social signals, utilizing partial and asynchronous evidence from video, text, and audio. We propose StreamSense, a streaming detector that couples a lightweight streaming encoder with selective routing to a Vision-Language Model (VLM) expert. StreamSense handles most timestamps with the lightweight streaming encoder, escalates hard/ambiguous cases to the VLM, and defers decisions when context is insufficient. The encoder is trained using (i) a cross-modal contrastive term to align visual/audio cues with textual signals, and (ii) an IoU-weighted loss that down-weights poorly overlapping target segments, mitigating label interference across segment boundaries. We evaluate StreamSense on multiple social streaming detection tasks (e.g., sentiment classification and hate content moderation), and the results show that StreamSense achieves higher accuracy than VLM-only streaming while only occasionally invoking the VLM, thereby reducing average latency and compute. Our results indicate that selective escalation and deferral are effective primitives for understanding streaming social tasks. Code is publicly available on GitHub.

Sketches, with their expressive potential, enable humans to convey the essence of an object through a rough contour. This work leverages expressive power for the first time to improve segmentation performance in challenging tasks such as camouflaged object detection (COD). We propose a sketch guided interactive segmentation framework that allows users to intuitively annotate objects with freehand sketches rather than relying on traditional bounding boxes or points commonly used in models such as the SAM. Our method introduces dedicated network architectural enhancements and a novel sketch augmentation strategy to fully exploit sketch input, leading to significant accuracy gains compared with text- or box-based annotations. Furthermore, our model's output can directly train other neural networks, achieving performance comparable to that of pixel-level annotations while reducing the annotation time by up to 120× and thereby lowering the barrier for large-scale dataset creation and model training. To support future research, werelease KOSCamo+, the first freehand sketch dataset for COD, along with code and a labeling tool. These contributions open promising avenues for expanding sketch-based interaction to broader segmentation tasks and exploring multimodal annotation strategies that combine sketches, text, and other lightweight user inputs.

This paper presents a novel approach for generating high-quality, cross-category 3D models from free-hand sketches with limited training data. We propose the first semi-supervised learning method to our knowledge for sketch-to-3D model conversion. Innovatively, we design a coarse-to-fine pipeline to perform the semi-supervised learning in the coarse stage and train a diffusion-based refiner to get a high-resolution 3D model. We designed a sketch-augmentation method for semi-supervised learning and integrated priors such as CLIP loss, shape prototypes, and adversarial loss to help generate high-quality results even with abstract and imprecise sketches. We also introduce an innovative procedural 3D generation method based on CAD code, which helps pre-train part of the network before fine-tuning with limited real data. Our approach, coupled with a specifically designed curriculum learning, allows us to generate high-quality 3D models across multiple categories with as few as 300 sketch-3D model pairs, marking a significant advancement over previous single-category approaches. In addition, we introduce the KO2D dataset, the largest collection of hand-drawn sketch-3D pairs to support further research in this area. As sketches are a far more intuitive and detailed way for users to express their unique ideas, we believe that this paper can move us closer to democratizing 3D content creation, enabling anyone to transform their ideas into 3D models effortlessly.

Existing LVLM-based reasoning segmentation methods often suffer from imprecise segmentation results and hallucinations in their text responses. This paper introduces POPEN, a novel framework designed to address these issues and achieve improved results. POPEN includes a preference-based optimization method to finetune the LVLM, aligning it more closely with human preferences and thereby generating better text responses and segmentation results. Additionally, POPEN introduces a preference-based ensemble method for inference, which integrates multiple outputs from the LVLM using a preference-score-based attention mechanism for refinement. To better adapt to the segmentation task, we incorporate several task-specific designs in our POPEN framework, including a new approach for collecting segmentation preference data with a curriculum learning mechanism, and a novel preference optimization loss to refine the segmentation capability of the LVLM. Experiments demonstrate that our method achieves state-of-the-art performance in reasoning segmentation, exhibiting minimal hallucination in text responses and the highest segmentation accuracy compared to previous advanced methods like LISA and PixelLM. Project page is here.

Few-Shot Segmentation (FSS) aims to learn class-agnostic segmentation on few classes to segment arbitrary classes, but at the risk of overfitting. To address this, some methods use the well-learned knowledge of foundation models (e.g., SAM) to simplify the learning process. Recently, SAM 2 has extended SAM by supporting video segmentation, whose class-agnostic matching ability is useful to FSS. A simple idea is to encode support foreground (FG) features as memory, with which query FG features are matched and fused. Unfortunately, the FG objects in different frames of SAM 2’s video data are always the same identity, while those in FSS are different identities, i.e., the matching step is incompatible. Therefore, we design Pseudo Prompt Generator to encode pseudo query memory, matching with query features in a compatible way. However, the memories can never be as accurate as the real ones, i.e., they are likely to contain incomplete query FG, and some unexpected query background (BG) features, leading to wrong segmentation. Hence, we further design Iterative Memory Refinement to fuse more query FG features into the memory, and devise a Support-Calibrated Memory Attention to suppress the unexpected query BG features in memory. Extensive experiments have been conducted on PASCAL-5$^i$ and COCO-20$^i$ to validate the effectiveness of our design, e.g., the 1-shot mIoU can be 4.2% better than the best baseline.

Referring MLLMs extend conventional multimodal large language models by allowing them to receive referring visual prompts and generate responses tailored to the indicated regions. However, these models often suffer from suboptimal performance due to incorrect responses tailored to misleading areas adjacent to or similar to the target region. This work introduces CPCF, a novel framework to address this issue and achieve superior results. CPCF contrasts outputs generated from the indicated visual prompt with those from contrastive prompts sampled from misleading regions, effectively suppressing the influence of erroneous information outside the target region on response generation. To further enhance the effectiveness and efficiency of our framework, several novel designs are proposed, including a prompt extraction network to automatically identify suitable contrastive prompts, a self-training method that leverages unlabeled data to improve training quality, and a distillation approach to reduce the additional computational overhead associated with contrastive decoding. Incorporating these novel designs, CPCF achieves state-of-the-art performance, as demonstrated by extensive experiments across multiple benchmarks. Project page: https://lanyunzhu.site/CPCF/

The success of DeepSeek-R1 demonstrates the immense potential of using reinforcement learning (RL) to enhance LLMs' reasoning capabilities. This paper introduces Retrv-R1, the first R1-style MLLM specifically designed for multimodal universal retrieval, achieving higher performance by employing step-by-step reasoning to produce more accurate retrieval results. We find that directly applying the methods of DeepSeek-R1 to retrieval tasks is not feasible, mainly due to (1) the high computational cost caused by the large token consumption required for multiple candidates with reasoning processes, and (2) the instability and suboptimal results when directly applying RL to train for retrieval tasks. To address these issues, Retrv-R1 introduces an information compression module with a details inspection mechanism, which enhances computational efficiency by reducing the number of tokens while ensuring that critical information for challenging candidates is preserved. Additionally, a new training paradigm is proposed, including an activation stage using a retrieval-tailored synthetic CoT dataset for more effective optimization, followed by RL with a novel curriculum reward to improve both performance and efficiency. Incorporating these novel designs, Retrv-R1 achieves SOTA performance, high efficiency, and strong generalization ability, as demonstrated by extensive experiments across multiple benchmarks and tasks.

Despite the rapid advancements in few-shot segmentation (FSS), most of existing methods in this domain are hampered by their reliance on the limited and biased information from only a small number of labeled samples. This limitation inherently restricts their capability to achieve sufficiently high levels of performance. To address this issue, this paper proposes a pioneering framework named LLaFS++, which, for the first time, applies large language models (LLMs) into FSS and achieves notable success. LLaFS++ leverages the extensive prior knowledge embedded by LLMs to guide the segmentation process, effectively compensating for the limited information contained in the few-shot labeled samples and thereby achieving superior results. To enhance the effectiveness of the text-based LLMs in FSS scenarios, we present several innovative and task-specific designs within the LLaFS++ framework. Specifically, we introduce an input instruction that allows the LLM to directly produce segmentation results represented as polygons, and propose a region-attribute corresponding table to simulate the human visual system and provide multi-modal guidance. We also synthesize pseudo samples and use curriculum learning for pretraining to augment data and achieve better optimization, and propose a novel inference method to mitigate potential oversegmentation hallucinations caused by the regional guidance information. Incorporating these designs, LLaFS++ constitutes an effective framework that achieves state-of-the-art results on multiple datasets including PASCAL-$5^{i}$5i, COCO-$20^{i}$20i, and FSS-1000. Our superior performance showcases the remarkable potential of applying LLMs to process few-shot vision tasks.

Continual Semantic Segmentation (CSS) extends static semantic segmentation by incrementally introducing new classes for training. To alleviate the catastrophic forgetting issue in this task, replay methods can be adopted, constructing a memory buffer that stores a small number of samples from previous classes for future replay. However, existing replay approaches in CSS often lack a thorough exploration of two critical issues: how to find the most suitable memory samples and how to utilize them for replay more effectively. Common strategies either randomly select samples or rely on hand-crafted, single-factor-driven methods that are hard to be optimal, and often employ conventional training techniques for replay that do not account for class imbalance problem resulting from limited memory capacity. In this work, we tackle these challenges by introducing a novel memory sample selection method that leverages a reinforcement learning framework with innovative state representations and a dual-stage action scheme to automatically learn a selection policy. Additionally, we propose an expert mechanism and a dual-phase training method to address the class imbalance issue, thereby enhancing the effectiveness of replay training by making better use of memory samples. Incorporating the proposed automatic sample selection and effective memory utilization methods, we develop a novel and effective replay-based pipeline for CSS. Our extensive experiments on Pascal VOC 2012 and ADE20 K datasets demonstrate the effectiveness of our approach, which achieves state-of-the-art (SOTA) performance and outperforms previous advanced methods significantly.

In this article, we propose Img2CAD, the first approach to our knowledge that uses 2-D image inputs to generate computer-aided design (CAD) models with editable parameters. Unlike existing artificial intelligence (AI) methods for 3-D model generation using text or image inputs often rely on mesh-based representations, which are incompatible with CAD tools and lack editability and fine control, Img2CAD enables seamless integration between AI-based 3-D reconstruction and CAD software. We have identified an innovative intermediate representation called structured visual geometry, characterized by vectorized wireframes extracted from objects. This representation significantly enhances the performance of generating conditioned CAD models. In addition, we introduce two new datasets to further support research in this area:a big cad model dataset (ABC)-mono, the largest known dataset comprising over 200 000 3-D CAD models with rendered images, andKOCAD, the first dataset featuring real-world captured objects alongside their ground truth CAD models, supporting further research in conditioned CAD model generation.

This paper proposes a new effective and efficient plug-and-play backbone for video-based person re-identification (ReID). Conventional video-based ReID methods typically use CNN or transformer backbones to extract deep features for every position in every sampled video frame. Here, we argue that this exhaustive feature extraction could be unnecessary, since we find that different frames in a ReID video often exhibit small differences and contain many similar regions due to the relatively slight movements of human beings. Inspired by this, a more selective, efficient paradigm is explored in this paper. Specifically, we introduce a patch selection mechanism to reduce computational cost by choosing only the crucial and non-repetitive patches for feature extraction. Additionally, we present a novel network structure that generates and utilizes pseudo frame global context to address the issue of incomplete views resulting from sparse inputs. By incorporating these new designs, our backbone can achieve both high performance and low computational cost. Extensive experiments on multiple datasets show that our approach reduces the computational cost by 74% compared to ViT-B and 28% compared to ResNet50, while the accuracy is on par with ViT-B and outperforms ResNet50 significantly.

In the era of immersive consumer electronics, such as AR/VR headsets and smart devices, people increasingly seek ways to express their identity through virtual fashion. However, existing 3D garment design tools remain inaccessible to everyday users due to steep technical barriers and limited data. In this work, we introduce a 3D sketch-driven 3D garment generation framework that empowers ordinary users - even those without design experience - to create high-quality digital clothing through simple 3D sketches in AR/VR environments. By combining a conditional diffusion model, a sketch encoder trained in a shared latent space, and an adaptive curriculum learning strategy, our system interprets imprecise, free-hand input and produces realistic, personalized garments. To address the scarcity of training data, we also introduce KO3DClothes, a new dataset of paired 3D garments and user-created sketches. Extensive experiments and user studies confirm that our method significantly outperforms existing baselines in both fidelity and usability, demonstrating its promise for democratized fashion design on next-generation consumer platforms.

This paper proposes LLaFS, the first attempt to leverage large language models (LLMs) in few-shot segmentation. In contrast to the conventional few-shot segmentation methods that only rely on the limited and biased information from the annotated support images, LLaFS leverages the vast prior knowledge gained by LLM as an effective supplement and directly uses the LLM to segment images in a few-shot manner. To enable the text-based LLM to handle image-related tasks, we carefully design an input instruction that allows the LLM to produce segmentation results represented as polygons, and propose a region-attribute table to simulate the human visual mechanism and provide multi-modal guidance. We also synthesize pseudo samples and use curriculum learning for pre-training to augment data and achieve better optimization. LLaFS achieves state-of-the-art results on multiple datasets, showing the potential of using LLMs for few-shot computer vision tasks.

Existing few-shot segmentation methods usually extract foreground prototypes from support images to guide query image segmentation. However, different background contexts of support and query images can cause their foreground features to be misaligned. This phenomenon, known as background context bias, can hinder the effectiveness of support prototypes in guiding query image segmentation. In this work, we propose a novel framework with an it-erative structure to address this problem. In each iteration of the framework, we first generate a query prediction based on a support foreground feature. Next, we extract background context from the query image to modulate the support foreground feature, thus eliminating the foreground feature misalignment caused by the different backgrounds. After that, we design a confidence-biased attention to eliminate noise and cleanse information. By integrating these components through an iterative structure, we create a novel network that can leverage the synergies between different modules to improve their performance in a mutually reinforcing manner. Through these carefully designed components and structures, our network can effectively elimi-nate background context bias in few-shot segmentation, thus achieving outstanding performance. We conduct extensive experiments on the PASCAL-5iand COCO-20idatasets and achieve state-of-the-art (SOTA) results, which demonstrate the effectiveness of our approach.

In this paper, we address the challenge of Perspective-Invariant Learning in machine learning and computer vision, which involves enabling a network to understand images from varying perspectives to achieve consistent semantic interpretation. While standard approaches rely on the labor-intensive collection of multi-view images or limited data augmentation techniques, we propose a novel framework, Discrete Latent Perspective Learning (DLPL), for latent multi-perspective fusion learning using conventional single-view images. DLPL comprises three main modules: Perspective Discrete Decomposition (PDD), Perspective Homography Transformation (PHT), and Perspective Invariant Attention (PIA), which work together to discretize visual features, transform perspectives, and fuse multi-perspective semantic information, respectively. DLPL is a universal perspective learning framework applicable to a variety of scenarios and vision tasks. Extensive experiments demonstrate that DLPL significantly enhances the network’s capacity to depict images across diverse scenarios (daily photos, UAV, auto-driving) and tasks (detection, segmentation).

Many few-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity. A recent advance Mamba can also well capture intra-sequence dependencies, yet the complexity is only linear. Hence, we aim to devise a cross (attention-like) Mamba to capture inter-sequence dependencies for FSS. A simple idea is to scan on support features to selectively compress them into the hidden state, which is then used as the initial hidden state to sequentially scan query features. Nevertheless, it suffers from (1) support forgetting issue: query features will also gradually be compressed when scanning on them, so the support features in hidden state keep reducing, and many query pixels cannot fuse sufficient support features; (2) intra-class gap issue: query FG is essentially more similar to itself rather than to support FG, i.e., query may prefer not to fuse support features but their own ones from the hidden state, yet the success of FSS relies on the effective use of support information. To tackle them, we design a hybrid Mamba network (HMNet), including (1) a support recapped Mamba to periodically recap the support features when scanning query, so the hidden state can always contain rich support information; (2) a query intercepted Mamba to forbid the mutual interactions among query pixels, and encourage them to fuse more support features from the hidden state. Consequently, the support information is better utilized, leading to better performance. Extensive experiments have been conducted on two public benchmarks, showing the superiority of HMNet. The code is available at https://github.com/Sam1224/HMNet.

The emerging trend of AR/VR places great demands on 3D content. However, most existing software requires expertise and is difficult for novice users to use. In this paper, we aim to create sketch-based modeling tools for user-friendly 3D modeling. We introduce Reality3DSketch with a novel application of an immersive 3D modeling experience, in which a user can capture the surrounding scene using a monocular RGB camera and can draw a single sketch of an object in the real-time reconstructed 3D scene. A 3D object is generated and placed in the desired location, enabled by our novel neural network with the input of a single sketch. Our neural network can predict the pose of a drawing and can turn a single sketch into a 3D model with view and structural awareness, which addresses the challenge of sparse sketch input and view ambiguity. We conducted extensive experiments synthetic and real-world datasets and achieved state-of-the-art (SOTA) results in both sketch view estimation and 3D modeling performance. According to our user study, our method of performing 3D modeling in a scene is$>$5x faster than conventional methods. Users are also more satisfied with the generated 3D model than the results of existing methods.

Continual Semantic Segmentation (CSS) extends static semantic segmentation by incrementally introducing new classes for training. To alleviate the catastrophic forgetting issue in CSS, a memory buffer that stores a small number of samples from the previous classes is constructed for replay. However, existing methods select the memory samples either randomly or based on a single-factor-driven handcrafted strategy, which has no guarantee to be optimal. In this work, we propose a novel memory sample selection mechanism that selects informative samples for effective replay in a fully automatic way by considering comprehensive factors including sample diversity and class performance. Our mechanism regards the selection operation as a decision-making process and learns an optimal selection policy that directly maximizes the validation performance on a reward set. To facilitate the selection decision, we design a novel state representation and a dual-stage action space. Our extensive experiments on Pascal-VOC 2012 and ADE 20K datasets demonstrate the effectiveness of our approach with state-of-the-art (SOTA) performance achieved, outperforming the second-place one by 12.54% for the 6-stage setting on Pascal-VOC 2012.

This work aims to investigate the problem of 3D modeling using single free-hand sketches, which is one of the most natural ways we humans express ideas. Although sketch-based 3D modeling can drastically make the 3D modeling process more accessible, the sparsity and ambiguity of sketches bring significant challenges for creating high-fidelity 3D models that reflect the creators’ ideas. In this work, we propose a view-and structural-aware deep learning approach, Deep3DSketch, which tackles the ambiguity and fully uses sparse information of sketches, emphasizing the structural information. Specifically, we introduced random pose sampling on both 3D shapes and 2D silhouettes, and an adversarial training scheme with an effective progressive discriminator to facilitate learning of the shape structures. Extensive experiments demonstrated the effectiveness of our approach, which outperforms existing methods – with state-of-the-art (SOTA) performance on both synthetic and real datasets.

Extracting and using class-discriminative features is critical for fine-grained recognition. Existing works have demonstrated the possibility of applying deep CNNs to exploit features that distinguish similar classes. However, CNNs suffer from problems including frequency bias and loss of detailed local information, which restricts the performance of recognizing fine-grained categories. To address the challenge, we propose a novel texture branch as complimentary to the CNN branch for feature extraction. We innovatively utilize Gabor filters as a powerful extractor to exploit texture features, motivated by the capability of Gabor filters in effectively capturing multi-frequency features and detailed local information. We implement several designs to enhance the effectiveness of Gabor filters, including imposing constraints on parameter values and developing a learning method to determine the optimal parameters. Moreover, we introduce a statistical feature extractor to utilize informative statistical information from the signals captured by Gabor filters, and a gate selection mechanism to enable efficient computation by only considering qualified regions as input for texture extraction. Through the integration of features from the Gabor-filter-based texture branch and CNN-based semantic branch, we achieve comprehensive information extraction. We demonstrate the efficacy of our method on multiple datasets, including CUB-200-2011, NA-bird, Stanford Dogs, and GTOS-mobile. State-of-the-art performance is achieved using our approach.

Medical image segmentation methods normally perform poorly when there is a domain shift between training and testing data. Unsupervised Domain Adaptation (UDA) addresses the domain shift problem by training the model using both labeled data from the source domain and unlabeled data from the target domain. Source-Free UDA (SFUDA) was recently proposed for UDA without requiring the source data during the adaptation, due to data privacy or data transmission issues, which normally adapts the pre-trained deep model in the testing stage. However, in real clinical scenarios of medical image segmentation, the trained model is normally frozen in the testing stage. In this paper, we propose Fourier Visual Prompting (FVP) for SFUDA of medical image segmentation. Inspired by prompting learning in natural language processing, FVP steers the frozen pre-trained model to perform well in the target domain by adding a visual prompt to the input target data. In FVP, the visual prompt is parameterized using only a small amount of low-frequency learnable parameters in the input frequency space, and is learned by minimizing the segmentation loss between the predicted segmentation of the prompted target image and reliable pseudo segmentation label of the target image under the frozen model. To our knowledge, FVP is the first work to apply visual prompts to SFUDA for medical image segmentation. The proposed FVP is validated using three public datasets, and experiments demonstrate that FVP yields better segmentation results, compared with various existing methods.

Large-scale training data with high-quality annotations is critical for training semantic and instance segmentation models. Unfortunately, pixel-wise annotation is labor-intensive and costly, raising the demand for more efficient labeling strategies. In this work, we present a novel 3D-to-2D label transfer method, Panoptic NeRF1, which aims for obtaining per-pixel 2D semantic and instance labels from easy-to-obtain coarse 3D bounding primitives. Our method utilizes NeRF as a differentiable tool to unify coarse 3D annotations and 2D semantic cues transferred from existing datasets. We demonstrate that this combination allows for improved geometry guided by semantic information, enabling rendering of accurate semantic maps across multiple views. Furthermore, this fusion process resolves label ambiguity of the coarse 3D annotations and filters noise in the 2D predictions. By inferring in 3D space and rendering to 2D labels, our 2D semantic and instance labels are multiview consistent by design. Experimental results show that Panoptic NeRF outperforms existing label transfer methods in terms of accuracy and multi-view consistency on challenging urban scenes of the KITTI-360 dataset.

Existing semantic segmentation works mainly focus on learning the contextual information in high-level semantic features with CNNs. In order to maintain a precise boundary, low-level texture features are directly skip-connected into the deeper layers. Nevertheless, texture features are not only about local structure, but also include global statistical knowledge of the input image. In this paper, we fully take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STL-Net) for semantic segmentation. For the first time, STL-Net analyzes the distribution of low level information and efficiently utilizes them for the task. Specifically, a novel Quantization and Counting Operator (QCO) is designed to describe the texture information in a statistical manner. Based on QCO, two modules are introduced: (1) Texture Enhance Module (TEM), to capture texture-related information and enhance the texture details; (2) Pyramid Texture Feature Extraction Module (PTFEM), to effectively extract the statistical texture features from multiple scales. Through extensive experiments, we show that the proposed STL-Net achieves state-of-the-art performance on three semantic segmentation benchmarks: Cityscapes, PASCAL Context and ADE20K.