3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed. However, the 3D Gaussians learned by 3D-GS have ambiguous structures without any geometry constraints. This inherent issue in 3D-GS leads to a rough boundary when segmenting individual objects. To remedy these problems, we propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS to improve segmentation accuracy while preserving segmentation speed. Specifically, we introduce a Gaussian Decomposition scheme, which ingeniously utilizes the special structure of 3D Gaussians, finds out, and then decomposes the boundary Gaussians. Moreover, to achieve fast interactive 3D segmentation, we introduce a novel training-free pipeline by lifting a 2D foundation model to 3D-GS. Extensive experiments demonstrate that our approach achieves high-quality 3D segmentation without rough boundary issues, which can be easily applied to other scene editing tasks. Our code is publicly available at https://github.com/XuHu0529/SAGS.

Developing comprehensive explicit world models is crucial for understanding and simulating real-world scenarios. Recently, Procedural Controllable Generation (PCG) has gained significant attention in large-scale scene generation by enabling the creation of scalable, high-quality assets. However, PCG faces challenges such as limited modular diversity, high expertise requirements, and challenges in managing the diverse elements and structures in complex scenes. In this paper, we introduce a large-scale scene generation framework, SceneX, which can automatically produce high-quality procedural models according to designers' textual descriptions. Specifically, the proposed method comprises two components, PCGHub and PCGPlanner. The former encompasses an extensive collection of accessible procedural assets and thousands of hand-craft API documents to perform as a standard protocol for PCG controller. The latter aims to generate executable actions for Blender to produce controllable and precise 3D assets guided by the user's instructions. Extensive experiments demonstrated the capability of our method in controllable large-scale scene generation, including nature scenes and unbounded cities, as well as scene editing such as asset placement and season translation.

Masked visual modeling has attracted much attention due to its promising potential in learning generalizable representations. Typical approaches urge models to predict specific contents of masked tokens, which can be intuitively considered as teaching a student (the model) to solve given problems (predicting masked contents). Under such settings, the performance is highly correlated with mask strategies (the difficulty of provided problems). We argue that it is equally important for the model to stand in the shoes of a teacher to produce challenging problems by itself. Intuitively, patches with high values of reconstruction loss can be regarded as hard samples, and masking those hard patches naturally becomes a demanding reconstruction task. To empower the model as a teacher, we propose Hard Patch Mining (HPM), predicting patch-wise losses and subsequently determining where to mask. Technically, we introduce an auxiliary loss predictor, which is trained with a relative objective to prevent overfitting to exact loss values. To gradually guide the training procedure, we propose an easy-to-hard mask strategy. Empirically, HPM brings significant improvements under both image and video benchmarks. Interestingly, solely incorporating the extra loss prediction objective leads to better representations, verifying the efficacy of determining where is hard to reconstruct.

For privacy and security concerns, the need to erase un-wanted information from pre-trained vision models is becoming evident nowadays. In real-world scenar-ios, erasure requests originate at any time from both users and model owners. These requests usually form a sequence. Therefore, under such a setting, selective information is expected to be continuously removed from a pre-trained model while maintaining the rest. We define this problem as continual forgetting and identify two key challenges. (i) For unwanted knowledge, efficient and effective deleting is crucial. (ii) For remaining knowledge, the impact brought by the forgetting procedure should be minimal. To address them, we propose Group Sparse LoRA (GS-LoRA). Specifically, towards (i), we use LoRA modules to fine-tune the FFN layers in Transformer blocks for each forgetting task independently, and towards (ii), a simple group sparse regularization is adopted, enabling automatic selection of specific LoRA groups and zeroing out the others. GS-LoRA is effective, parameter-efficient, data-efficient, and easy to implement. We conduct extensive experiments on face recognition, object detection and image classification and demonstrate that GS-LoRA manages to forget specific classes with minimal impact on other classes. Codes will be released on https://github.com/bjzhb666/GS-LoRA.

Recent years have witnessed rapid progress in monoc-ular human mesh recovery. Despite their impressive performance on public benchmarks, existing methods are vulnerable to unusual poses, which prevents them from deploying to challenging scenarios such as dance and martial arts. This issue is mainly attributed to the domain gap induced by the data scarcity in relevant cases. Most existing datasets are captured in constrained scenarios and lack samples of such complex movements. For this reason, we propose a data collection pipeline comprising automatic crawling, precise annotation, and hardcase mining. Based on this pipeline, we establish a large dataset in a short time. The dataset, named HardMo, contains 7M images along with precise annotations covering 15 categories of dance and 14 categories of martial arts. Empirically, we find that the prediction failure in dance and martial arts is mainly characterized by the misalignment of hand-wrist and foot-ankle. To dig deeper into the two hardcases, we leverage the proposed automatic pipeline to filter collected data and construct two subsets named HardMo-Hand and HardMo-Foot. Extensive experiments demonstrate the effectiveness of the annotation pipeline and the data-driven solution to failure cases. Specifically, after being trained on HardMo, HMR, an early pioneering method, can even outperform the current state of the art, 4DHumans, on our benchmarks. Dataset will be publicly available at https://ljqnb.github.io/HardMo.github.io.

Thanks to the powerful generative capacity of diffusion models, recent years have witnessed rapid progress in human motion generation. Existing diffusion-based methods employ disparate network architectures and training strategies. The effect of the design of each component is still unclear. In addition, the iterative denoising process consumes considerable computational overhead, which is prohibitive for real-time scenarios such as virtual characters and humanoid robots. For this reason, we first conduct a comprehensive investigation into network architectures, training strategies, and inference process. Based on the profound analysis, we tailor each component for efficient high-quality human motion generation. Despite the promising performance, the tailored model still suffers from foot skating which is an ubiquitous issue in diffusion-based solutions. To eliminate footskate, we identify foot-ground contact and correct foot motions along the denoising process. By organically combining these well-designed components together, we present StableMoFusion, a robust and efficient framework for human motion generation. Extensive experimental results show that our StableMoFusion performs favorably against current state-of-the-art methods.

Driven by powerful image diffusion models, recent research has achieved the automatic creation of 3D objects from textual or visual guidance. By performing score distillation sampling (SDS) iteratively across different views, these methods succeed in lifting 2D generative prior to the 3D space. However, such a 2D generative image prior bakes the effect of illumination and shadow into the texture. As a result, material maps optimized by SDS inevitably involve spurious correlated components. The absence of precise material definition makes it infeasible to relight the generated assets reasonably in novel scenes, which limits their application in downstream scenarios. In contrast, humans can effortlessly circumvent this ambiguity by deducing the material of the object from its appearance and semantics. Motivated by this insight, we propose MaterialSeg3D, a 3D asset material generation framework to infer underlying material from the 2D semantic prior. Based on such a prior model, we devise a mechanism to parse material in 3D space. We maintain a UV stack, each map of which is unprojected from a specific viewpoint. After traversing all viewpoints, we fuse the stack through a weighted voting scheme and then employ region unification to ensure the coherence of the object parts. To fuel the learning of semantics prior, we collect a material dataset, named Materialized Individual Objects (MIO), which features abundant images, diverse categories, and accurate annotations. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method.

Sound source localization aims to localize objects emitting the sound in visual scenes. Recent works obtaining impressive results typically rely on contrastive learning. However, the common practice of randomly sampling negatives in prior arts can lead to the false negative issue, where the sounds semantically similar to visual instance are sampled as negatives and incorrectly pushed away from the visual anchor/query. As a result, this misalignment of audio and visual features could yield inferior performance. To address this issue, we propose a novel audio-visual learning framework which is instantiated with two individual learning schemes: self-supervised predictive learning (SSPL) and semantic-aware contrastive learning (SACL). SSPL explores image-audio positive pairs alone to discover semantically coherent similarities between audio and visual features, while a predictive coding module for feature alignment is introduced to facilitate the positive-only learning. In this regard SSPL acts as a negative-free method to eliminate false negatives. By contrast, SACL is designed to compact visual features and remove false negatives, providing reliable visual anchor and audio negatives for contrast. Different from SSPL, SACL releases the potential of audio-visual contrastive learning, offering an effective alternative to achieve the same goal. Comprehensive experiments demonstrate the superiority of our approach over the state-of-the-arts. Furthermore, we highlight the versatility of the learned representation by extending the approach to audio-visual event classification and object detection tasks.

Source-free domain adaptation has developed rapidly in recent years, where the well-trained source model is adapted to the target domain instead of the source data, offering the potential for privacy concerns and intellectual property protection. However, a number of feature alignment techniques in prior domain adaptation methods are not feasible in this challenging problem setting. Thereby, we resort to probing inherent domain-invariant feature learning and propose a curriculum-style self-training approach for source-free domain adaptive semantic segmentation. In particular, we introduce a curriculum-style entropy minimization method to explore the implicit knowledge from the source model, which fits the trained source model to the target data using certain information from easy-to-hard predictions. We then train the segmentation network by the proposed complementary curriculum-style self-training, which utilizes the negative and positive pseudo labels following the curriculum-learning manner. Although negative pseudo-labels with high uncertainty cannot be identified with the correct labels, they can definitely indicate absent classes. Moreover, we employ an information propagation scheme to further reduce the intra-domain discrepancy within the target domain, which could act as a standard post-processing method for the domain adaptation field. Furthermore, we extend the proposed method to a more challenging black-box source model scenario where only the source model's predictions are available. Extensive experiments validate that our method yields state-of-the-art performance on source-free semantic segmentation tasks for both synthetic-to-real and adverse conditions datasets.

Masked image modeling (MIM) has attracted much research attention due to its promising potential for learning scalable visual representations. In typical approaches, models usually focus on predicting specific contents of masked patches, and their performances are highly related to pre-defined mask strategies. Intuitively, this procedure can be considered as training a student (the model) on solving given problems (predict masked patches). However, we argue that the model should not only focus on solving given problems, but also stand in the shoes of a teacher to produce a more challenging problem by itself. To this end, we propose Hard Patches Mining (HPM), a brand-new framework for MIM pre-training. We observe that the reconstruction loss can naturally be the metric of the difficulty of the pretraining task. Therefore, we introduce an auxiliary loss predictor, predicting patch-wise losses first and deciding where to mask next. It adopts a relative relationship learning strategy to prevent overfitting to exact reconstruction loss values. Experiments under various settings demonstrate the effectiveness of HPM in constructing masked images. Furthermore, we empirically find that solely introducing the loss prediction objective leads to powerful representations, verifying the efficacy of the ability to be aware of where is hard to reconstruct.11Code: https://github.com/Haochen-wang409/HPM

Contemporary domain adaptation offers a practical solution for achieving cross-domain transfer of semantic segmentation between labelled source data and unlabeled target data. These solutions have gained significant popularity; however, they require the model to be retrained when the test environment changes. This can result in unbearable costs in certain applications due to the time-consuming training process and concerns regarding data privacy. One-shot domain adaptation methods attempt to overcome these challenges by transferring the pre-trained source model to the target domain using only one target data. Despite this, the referring style transfer module still faces issues with computation cost and over-fitting problems. To address this problem, we propose a novel framework called Informative Data Mining (IDM) that enables efficient one-shot domain adaptation for semantic segmentation. Specifically, IDM provides an uncertainty-based selection criterion to identify the most informative samples, which facilitates quick adaptation and reduces redundant training. We then perform a model adaptation method using these selected samples, which includes patch-wise mixing and prototype-based information maximization to update the model. This approach effectively enhances adaptation and mitigates the overfitting problem. In general, we provide empirical evidence of the effectiveness and efficiency of IDM. Our approach outperforms existing methods and achieves a new state-of-the-art one-shot performance of 56.7%/55.4% on the GTA5/SYNTHIA to Cityscapes adaptation tasks, respectively. The code will be released at https://github.com/yxiwang/IDM.

Surrogate gradient (SG) is one of the most effective approaches for training spiking neural networks (SNNs). While assisting SNNs to achieve classification performance comparable to artificial neural networks, SG suffers from the problem of time-consuming training, preventing it from efficient learning. In this paper, we formally analyze the backward process of classic SG and find that the membrane accumulation through time leads to exponential growth of training time. With this discovery, we propose Stabilized Spiking Flow (SSF), a simple yet effective approach to accelerate training of SG-based SNNs. For each spiking neuron, SSF averages its input and output activations over time to yield stabilized input and output, respectively. Then, instead of back propagating all errors that are related to current neuron and inherently entangled in time domain, the auxiliary gradient is directly propagated from the stabilized output to input through a devised relationship mapping. Additionally, SSF method is suitable to different neuron models. Extensive experiments on both static and neuromorphic datasets demonstrate that SNNs trained with SSF approach can achieve performance comparable to the original counterparts, while reducing the training time significantly. In particular, SSF speeds up the training process of state-of-the-art SNN models up to 10× when time steps equal to 80.

As it is empirically observed that Vision Transformers (ViTs) are quite insensitive to the order of input tokens, the need for an appropriate self-supervised pretext task that enhances the location awareness of ViTs is becoming evident. To address this, we present DropPos, a novel pretext task designed to reconstruct Dropped Positions. The formulation of DropPos is simple: we first drop a large random subset of positional embeddings and then the model classifies the actual position for each non-overlapping patch among all possible positions solely based on their visual appearance. To avoid trivial solutions, we increase the difficulty of this task by keeping only a subset of patches visible. Additionally, considering there may be different patches with similar visual appearances, we propose position smoothing and attentive reconstruction strategies to relax this classification problem, since it is not necessary to reconstruct their exact positions in these cases. Empirical evaluations of DropPos show strong capabilities. DropPos outperforms supervised pre-training and achieves competitive results compared with state-of-the-art self-supervised alternatives on a wide range of downstream benchmarks. This suggests that explicitly encouraging spatial reasoning abilities, as DropPos does, indeed contributes to the improved location awareness of ViTs. The code is publicly available at https://github.com/Haochen-Wang409/DropPos.

Few-shot learning aims to recognize novel categories solely relying on a few labeled samples, with existing few-shot methods primarily focusing on the categories sampled from the same distribution. Nevertheless, this assumption cannot always be ensured, and the actual domain shift problem significantly reduces the performance of few-shot learning. To remedy this problem, we investigate an interesting and challenging cross-domain few-shot learning task, where the training and testing tasks employ different domains. Specifically, we propose a Meta-Memory scheme to bridge the domain gap between source and target domains, leveraging style-memory and content-memory components. The former stores intra-domain style information from source domain instances and provides a richer feature distribution. The latter stores semantic information through exploration of knowledge of different categories. Under the contrastive learning strategy, our model effectively alleviates the cross-domain problem in few-shot learning. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on cross-domain few-shot semantic segmentation tasks on the COCO-20$^{i}$, PASCAL-5$^{i}$, FSS-1000, and SUIM datasets and positively affects few-shot classification tasks on Meta-Dataset.

Interactive object segmentation aims to produce object masks with user interactions, such as clicks, bounding boxes, and scribbles. Click point is the most popular interactive cue for its efficiency, and related deep learning methods have attracted lots of interest in recent years. Most works encode click points as gaussian maps and concatenate them with images as the model's input. However, the spatial and semantic information of gaussian maps would be noised through multiple convolution layers and won't be fully exploited by top layers for mask prediction. To pass click information to top layers exactly and efficiently, we propose a coarse mask guided model (CMG) which predicts coarse masks with a coarse module to guide the object mask prediction. Specifically, the coarse module encodes user clicks as query features and enriches their semantic information with backbone features through transformer layers, coarse masks are generated based on the enriched query feature and fed into CMG's decoder. Benefiting from the efficiency of transformer, CMG's coarse module and decoder module are lightweight and computationally efficient, making the interaction process more smooth. Experiments on several segmentation benchmarks demonstrate the effectiveness of our method, and we get new state-of-the-art results compared with previous works.

Few-shot semantic segmentation intends to predict pixel-level categories using only a few labeled samples. Existing few-shot methods focus primarily on the categories sampled from the same distribution. Nevertheless, this assumption cannot always be ensured. The actual domain shift problem significantly reduces the performance of few-shot learning. To remedy this problem, we propose an interesting and challenging cross-domain few-shot semantic segmentation task, where the training and test tasks perform on different domains. Specifically, we first propose a meta-memory bank to improve the generalization of the segmentation network by bridging the domain gap between source and target domains. The meta-memory stores the intra-domain style information from source domain instances and transfers it to target samples. Subsequently, we adopt a new contrastive learning strategy to explore the knowledge of different categories during the training stage. The negative and positive pairs are obtained from the proposed memory-based style augmentation. Comprehensive experiments demon-strate that our proposed method achieves promising results on cross-domain few-shot semantic segmentation tasks on COCO-20i, PASCAL-Si, FSS-1000, and SUIM datasets.

Existing interactive segmentation methods mainly focus on optimizing user interacting strategies, as well as making better use of clicks provided by users. However, the intention of the interactive segmentation model is to obtain high-quality masks with limited user interactions, which are supposed to be applied to unlabeled new images. But most existing methods overlooked the generalization ability of their models when witnessing new target scenes. To overcome this problem, we propose a life-long evolution framework for interactive models in this paper, which provides a possible solution for dealing with dynamic target scenes with one single model. Given several target scenes and an initial model trained with labels on the limited closed dataset, our framework arranges sequentially evolution steps on each target set. Specifically, we propose an interactive-prototype module to generate and refine pseudo masks, and apply a feature alignment module in order to adapt the model to a new target scene and keep the performance on previous images at the same time. All evolution steps above do not require ground truth labels as supervision. We conduct thorough experiments on PASCAL VOC, Cityscapes, and COCO datasets, demonstrating the effectiveness of our framework in solving new target datasets and maintaining performance on previous scenes at the same time.

Unsupervised domain adaptation for semantic segmentation aims to assign the pixel-level labels for unlabeled target domain by transferring knowledge from the labeled source domain. A typical self-supervised learning approach generates pseudo labels from the source model and then re-trains the model to fit the target distribution. However, it suffers from noisy pseudo labels due to the existence of domain shift. Related works alleviate this problem by selecting high-confidence predictions, but uncertain classes with low confidence scores have rarely been considered. This informative uncertainty is essential to enhance feature representation and align source and target domains. In this paper, we propose a novel uncertainty-aware pseudo label refinery framework considering two crucial factors simultaneously. First, we progressively enhance the feature alignment model via the target-guided uncertainty rectifying framework. Second, we provide an uncertainty-aware pseudo label assignment strategy without any manually de-signed threshold to reduce the noisy labels. Extensive experiments demonstrate the effectiveness of our proposed approach and achieve state-of-the-art performance on two standard synthetic-2-real tasks.

The image-to-image translation aims to learn the corresponding information between the source and target domains. Several state-of-the-art works have made significant progress based on generative adversarial networks (GANs). However, most existing one-to-one translation methods ignore the correlations among different domain pairs. We argue that there is common information among different domain pairs and it is vital to multiple domain pairs translation. In this paper, we propose a unified circular framework for multiple domain pairs translation, leveraging a shared knowledge module across numerous domains. One selected translation pair can benefit from the complementary information from other pairs, and the sharing knowledge is conducive to mutual learning between domains. Moreover, absolute consistency loss is proposed and applied in the corresponding feature maps to ensure intra-domain consistency. Furthermore, our model can be trained in an end-to-end manner. Extensive experiments demonstrate the effectiveness of our approach on several complex translation scenarios, such as Thermal IR switching, weather changing, and semantic transfer tasks.

Domain adaptation aims to alleviate the distribution discrepancy between source and target domains. Most conventional methods focus on one target domain setting adapted from one or multiple source domains while neglecting the multi-target domain setting. We argue that different target domains also have complementary information, which is very important for performance improvement. In this paper, we propose an Attention-guided Multiple source-and-target Domain Adaptation (AMDA) method to capture the context dependency information on transferable regions among multiple source and target domains. The innovation points of this paper are as follows: (1) We use numerous adversarial strategies to harvest sufficient information from multiple source and target domains, which extends the generalization and robustness of the feature pools. (2) We propose an intra-domain and inter-domain attention module to explore transferable context information. The proposed attention module can learn domain-invariant representations and reduce the negative transfer by focusing on transferable knowledge. Extensive experiments validate the effectiveness of our method with achieving state-of-the-art performance on several unsupervised domain adaptation datasets.