Xiangtai Li

Xiangtai Li, Henghui Ding, Haobo Yuan et al.

Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical analysis. Over the past decade, deep learning-based methods have made remarkable strides in this area. Recently, transformers, a type of neural network based on self-attention originally designed for natural language processing, have considerably surpassed previous convolutional or recurrent approaches in various vision processing tasks. Specifically, vision transformers offer robust, unified, and even simpler solutions for various segmentation tasks. This survey provides a thorough overview of transformer-based visual segmentation, summarizing recent advancements. We first review the background, encompassing problem definitions, datasets, and prior convolutional methods. Next, we summarize a meta-architecture that unifies all recent transformer-based approaches. Based on this meta-architecture, we examine various method designs, including modifications to the meta-architecture and associated applications. We also present several closely related settings, including 3D point cloud segmentation, foundation model tuning, domain-aware segmentation, efficient segmentation, and medical segmentation. Additionally, we compile and re-evaluate the reviewed methods on several well-established datasets. Finally, we identify open challenges in this field and propose directions for future research. The project page can be found at https://github.com/lxtGH/Awesome-Segmentation-With-Transformer. We will also continually monitor developments in this rapidly evolving field.

Yibo Yang, Haobo Yuan, Xiangtai Li et al.

Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. Finetuning the backbone or adjusting the classifier prototypes trained in the prior sessions would inevitably cause a misalignment between the feature and classifier of old classes, which explains the well-known catastrophic forgetting problem. In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same class will collapse into a vertex, and the vertices of all classes are aligned with the classifier prototypes, which are formed as a simplex equiangular tight frame (ETF). It corresponds to an optimal geometric structure for classification due to the maximized Fisher Discriminant Ratio. We propose a neural collapse inspired framework for FSCIL. A group of classifier prototypes are pre-assigned as a simplex ETF for the whole label space, including the base session and all the incremental sessions. During training, the classifier prototypes are not learnable, and we adopt a novel loss function that drives the features into their corresponding prototypes. Theoretical analysis shows that our method holds the neural collapse optimality and does not break the feature-classifier alignment in an incremental fashion. Experiments on the miniImageNet, CUB-200, and CIFAR-100 datasets demonstrate that our proposed framework outperforms the state-of-the-art performances. Code address: https://github.com/NeuralCollapseApplications/FSCIL

Xiangtai Li, Wenwei Zhang, Jiangmiao Pang et al.

This paper presents Video K-Net, a simple, strong, and unified framework for fully end-to-end video panoptic segmentation. The method is built upon K-Net, a method that unifies image segmentation via a group of learnable kernels. We observe that these learnable kernels from K-Net, which encode object appearances and contexts, can naturally associate identical instances across video frames. Motivated by this observation, Video K-Net learns to simultaneously segment and track "things" and "stuff" in a video with simple kernel-based appearance modeling and cross-temporal kernel interaction. Despite the simplicity, it achieves state-of-the-art video panoptic segmentation results on Citscapes-VPS, KITTI-STEP, and VIPSeg without bells and whistles. In particular, on KITTI-STEP, the simple method can boost almost 12\% relative improvements over previous methods. On VIPSeg, Video K-Net boosts almost 15\% relative improvements and results in 39.8 % VPQ. We also validate its generalization on video semantic segmentation, where we boost various baselines by 2\% on the VSPW dataset. Moreover, we extend K-Net into clip-level video framework for video instance segmentation, where we obtain 40.5% mAP for ResNet50 backbone and 54.1% mAP for Swin-base on YouTube-2019 validation set. We hope this simple, yet effective method can serve as a new, flexible baseline in unified video segmentation design. Both code and models are released at https://github.com/lxtGH/Video-K-Net.

Jianzong Wu, Xiangtai Li, Shilin Xu et al.

In the field of visual scene understanding, deep neural networks have made impressive advancements in various core tasks like segmentation, tracking, and detection. However, most approaches operate on the close-set assumption, meaning that the model can only identify pre-defined categories that are present in the training set. Recently, open vocabulary settings were proposed due to the rapid progress of vision language pre-training. These new approaches seek to locate and recognize categories beyond the annotated label space. The open vocabulary approach is more general, practical, and effective compared to weakly supervised and zero-shot settings. This paper provides a thorough review of open vocabulary learning, summarizing and analyzing recent developments in the field. In particular, we begin by comparing it to related concepts such as zero-shot learning, open-set recognition, and out-of-distribution detection. Then, we review several closely related tasks in the case of segmentation and detection, including long-tail problems, few-shot, and zero-shot settings. For the method survey, we first present the basic knowledge of detection and segmentation in close-set as the preliminary knowledge. Next, we examine various scenarios in which open vocabulary learning is used, identifying common design elements and core ideas. Then, we compare the recent detection and segmentation approaches in commonly used datasets and benchmarks. Finally, we conclude with insights, issues, and discussions regarding future research directions. To our knowledge, this is the first comprehensive literature review of open vocabulary learning. We keep tracing related works at https://github.com/jianzongwu/Awesome-Open-Vocabulary.

Jingkang Yang, Wenxuan Peng, Xiangtai Li et al. · stanford

Towards building comprehensive real-world visual perception systems, we propose and study a new problem called panoptic scene graph generation (PVSG). PVSG relates to the existing video scene graph generation (VidSGG) problem, which focuses on temporal interactions between humans and objects grounded with bounding boxes in videos. However, the limitation of bounding boxes in detecting non-rigid objects and backgrounds often causes VidSGG to miss key details crucial for comprehensive video understanding. In contrast, PVSG requires nodes in scene graphs to be grounded by more precise, pixel-level segmentation masks, which facilitate holistic scene understanding. To advance research in this new area, we contribute the PVSG dataset, which consists of 400 videos (289 third-person + 111 egocentric videos) with a total of 150K frames labeled with panoptic segmentation masks as well as fine, temporal scene graphs. We also provide a variety of baseline methods and share useful design practices for future work.

Xiangtai Li, Shilin Xu, Yibo Yang et al.

Panoptic Part Segmentation (PPS) aims to unify panoptic segmentation and part segmentation into one task. Previous work mainly utilizes separated approaches to handle thing, stuff, and part predictions individually without performing any shared computation and task association. In this work, we aim to unify these tasks at the architectural level, designing the first end-to-end unified method named Panoptic-PartFormer. In particular, motivated by the recent progress in Vision Transformer, we model things, stuff, and part as object queries and directly learn to optimize the all three predictions as unified mask prediction and classification problem. We design a decoupled decoder to generate part feature and thing/stuff feature respectively. Then we propose to utilize all the queries and corresponding features to perform reasoning jointly and iteratively. The final mask can be obtained via inner product between queries and the corresponding features. The extensive ablation studies and analysis prove the effectiveness of our framework. Our Panoptic-PartFormer achieves the new state-of-the-art results on both Cityscapes PPS and Pascal Context PPS datasets with at least 70% GFlops and 50% parameters decrease. In particular, we get 3.4% relative improvements with ResNet50 backbone and 10% improvements after adopting Swin Transformer on Pascal Context PPS dataset. To the best of our knowledge, we are the first to solve the PPS problem via \textit{a unified and end-to-end transformer model. Given its effectiveness and conceptual simplicity, we hope our Panoptic-PartFormer can serve as a good baseline and aid future unified research for PPS. Our code and models are available at https://github.com/lxtGH/Panoptic-PartFormer.

Jiahao Xie, Wei Li, Xiangtai Li et al.

We present MosaicFusion, a simple yet effective diffusion-based data augmentation approach for large vocabulary instance segmentation. Our method is training-free and does not rely on any label supervision. Two key designs enable us to employ an off-the-shelf text-to-image diffusion model as a useful dataset generator for object instances and mask annotations. First, we divide an image canvas into several regions and perform a single round of diffusion process to generate multiple instances simultaneously, conditioning on different text prompts. Second, we obtain corresponding instance masks by aggregating cross-attention maps associated with object prompts across layers and diffusion time steps, followed by simple thresholding and edge-aware refinement processing. Without bells and whistles, our MosaicFusion can produce a significant amount of synthetic labeled data for both rare and novel categories. Experimental results on the challenging LVIS long-tailed and open-vocabulary benchmarks demonstrate that MosaicFusion can significantly improve the performance of existing instance segmentation models, especially for rare and novel categories. Code: https://github.com/Jiahao000/MosaicFusion.

Shilin Xu, Xiangtai Li, Jingbo Wang et al.

Human fashion understanding is one crucial computer vision task since it has comprehensive information for real-world applications. This focus on joint human fashion segmentation and attribute recognition. Contrary to the previous works that separately model each task as a multi-head prediction problem, our insight is to bridge these two tasks with one unified model via vision transformer modeling to benefit each task. In particular, we introduce the object query for segmentation and the attribute query for attribute prediction. Both queries and their corresponding features can be linked via mask prediction. Then we adopt a two-stream query learning framework to learn the decoupled query representations.We design a novel Multi-Layer Rendering module for attribute stream to explore more fine-grained features. The decoder design shares the same spirit as DETR. Thus we name the proposed method \textit{Fahsionformer}. Extensive experiments on three human fashion datasets illustrate the effectiveness of our approach. In particular, our method with the same backbone achieve \textbf{relative 10\% improvements} than previous works in case of \textit{a joint metric (AP$^{\text{mask}}_{\text{IoU+F}_1}$) for both segmentation and attribute recognition}. To the best of our knowledge, we are the first unified end-to-end vision transformer framework for human fashion analysis. We hope this simple yet effective method can serve as a new flexible baseline for fashion analysis. Code is available at https://github.com/xushilin1/FashionFormer.

Xiangtai Li, Shilin Xu, Yibo Yang et al.

Panoptic Part Segmentation (PPS) unifies panoptic and part segmentation into one task. Previous works utilize separate approaches to handle things, stuff, and part predictions without shared computation and task association. We aim to unify these tasks at the architectural level, designing the first end-to-end unified framework, Panoptic-PartFormer. Moreover, we find the previous metric PartPQ biases to PQ. To handle both issues, we first design a meta-architecture that decouples part features and things/stuff features, respectively. We model things, stuff, and parts as object queries and directly learn to optimize all three forms of prediction as a unified mask prediction and classification problem. We term our model as Panoptic-PartFormer. Second, we propose a new metric Part-Whole Quality (PWQ), better to measure this task from pixel-region and part-whole perspectives. It also decouples the errors for part segmentation and panoptic segmentation. Third, inspired by Mask2Former, based on our meta-architecture, we propose Panoptic-PartFormer++ and design a new part-whole cross-attention scheme to boost part segmentation qualities further. We design a new part-whole interaction method using masked cross attention. Finally, extensive ablation studies and analysis demonstrate the effectiveness of both Panoptic-PartFormer and Panoptic-PartFormer++. Compared with previous Panoptic-PartFormer, our Panoptic-PartFormer++ achieves 2% PartPQ and 3% PWQ improvements on the Cityscapes PPS dataset and 5% PartPQ on the Pascal Context PPS dataset. On both datasets, Panoptic-PartFormer++ achieves new state-of-the-art results. Our models can serve as a strong baseline and aid future research in PPS. The source code and trained models will be available at~\url{https://github.com/lxtGH/Panoptic-PartFormer}.

Yangyang Xu, Xiangtai Li, Haobo Yuan et al.

Previous multi-task dense prediction studies developed complex pipelines such as multi-modal distillations in multiple stages or searching for task relational contexts for each task. The core insight beyond these methods is to maximize the mutual effects of each task. Inspired by the recent query-based Transformers, we propose a simple pipeline named Multi-Query Transformer (MQTransformer) that is equipped with multiple queries from different tasks to facilitate the reasoning among multiple tasks and simplify the cross-task interaction pipeline. Instead of modeling the dense per-pixel context among different tasks, we seek a task-specific proxy to perform cross-task reasoning via multiple queries where each query encodes the task-related context. The MQTransformer is composed of three key components: shared encoder, cross-task query attention module and shared decoder. We first model each task with a task-relevant query. Then both the task-specific feature output by the feature extractor and the task-relevant query are fed into the shared encoder, thus encoding the task-relevant query from the task-specific feature. Secondly, we design a cross-task query attention module to reason the dependencies among multiple task-relevant queries; this enables the module to only focus on the query-level interaction. Finally, we use a shared decoder to gradually refine the image features with the reasoned query features from different tasks. Extensive experiment results on two dense prediction datasets (NYUD-v2 and PASCAL-Context) show that the proposed method is an effective approach and achieves state-of-the-art results. Code and models are available at https://github.com/yangyangxu0/MQTransformer.

Jianzong Wu, Xiangtai Li, Xia Li et al.

Referring Image Segmentation (RIS) is a fundamental vision-language task that outputs object masks based on text descriptions. Many works have achieved considerable progress for RIS, including different fusion method designs. In this work, we explore an essential question, ``What if the text description is wrong or misleading?'' For example, the described objects are not in the image. We term such a sentence as a negative sentence. However, existing solutions for RIS cannot handle such a setting. To this end, we propose a new formulation of RIS, named Robust Referring Image Segmentation (R-RIS). It considers the negative sentence inputs besides the regular positive text inputs. To facilitate this new task, we create three R-RIS datasets by augmenting existing RIS datasets with negative sentences and propose new metrics to evaluate both types of inputs in a unified manner. Furthermore, we propose a new transformer-based model, called RefSegformer, with a token-based vision and language fusion module. Our design can be easily extended to our R-RIS setting by adding extra blank tokens. Our proposed RefSegformer achieves state-of-the-art results on both RIS and R-RIS datasets, establishing a solid baseline for both settings. Our project page is at \url{https://github.com/jianzongwu/robust-ref-seg}.

Jiangning Zhang, Xiangtai Li, Yabiao Wang et al.

Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical evolutionary algorithm (EA) and derives that both have consistent mathematical formulation. Then inspired by effective EA variants, we propose a novel pyramid EATFormer backbone that only contains the proposed EA-based transformer (EAT) block, which consists of three residual parts, i.e., Multi-scale region aggregation, global and local interaction, and feed-forward network modules, to model multi-scale, interactive, and individual information separately. Moreover, we design a task-related head docked with transformer backbone to complete final information fusion more flexibly and improve a modulated deformable MSA to dynamically model irregular locations. Massive quantitative and quantitative experiments on image classification, downstream tasks, and explanatory experiments demonstrate the effectiveness and superiority of our approach over state-of-the-art methods. E.g., our Mobile (1.8 M), Tiny (6.1 M), Small (24.3 M), and Base (49.0 M) models achieve 69.4, 78.4, 83.1, and 83.9 Top-1 only trained on ImageNet-1K with naive training recipe; EATFormer-Tiny/Small/Base armed Mask-R-CNN obtain 45.4/47.4/49.0 box AP and 41.4/42.9/44.2 mask AP on COCO detection, surpassing contemporary MPViT-T, Swin-T, and Swin-S by 0.6/1.4/0.5 box AP and 0.4/1.3/0.9 mask AP separately with less FLOPs; Our EATFormer-Small/Base achieve 47.3/49.3 mIoU on ADE20K by Upernet that exceeds Swin-T/S by 2.8/1.7. Code is available at https://github.com/zhangzjn/EATFormer.

Xiangtai Li, Jiangning Zhang, Yibo Yang et al.

In this paper, we focus on exploring effective methods for faster and accurate semantic segmentation. A common practice to improve the performance is to attain high-resolution feature maps with strong semantic representation. Two strategies are widely used: atrous convolutions and feature pyramid fusion, while both are either computationally intensive or ineffective. Inspired by the Optical Flow for motion alignment between adjacent video frames, we propose a Flow Alignment Module (FAM) to learn \textit{Semantic Flow} between feature maps of adjacent levels and broadcast high-level features to high-resolution features effectively and efficiently. Furthermore, integrating our FAM to a standard feature pyramid structure exhibits superior performance over other real-time methods, even on lightweight backbone networks, such as ResNet-18 and DFNet. Then to further speed up the inference procedure, we also present a novel Gated Dual Flow Alignment Module to directly align high-resolution feature maps and low-resolution feature maps where we term the improved version network as SFNet-Lite. Extensive experiments are conducted on several challenging datasets, where results show the effectiveness of both SFNet and SFNet-Lite. In particular, when using Cityscapes test set, the SFNet-Lite series achieve 80.1 mIoU while running at 60 FPS using ResNet-18 backbone and 78.8 mIoU while running at 120 FPS using STDC backbone on RTX-3090. Moreover, we unify four challenging driving datasets into one large dataset, which we named Unified Driving Segmentation (UDS) dataset. It contains diverse domain and style information. We benchmark several representative works on UDS. Both SFNet and SFNet-Lite still achieve the best speed and accuracy trade-off on UDS, which serves as a strong baseline in such a challenging setting. The code and models are publicly available at https://github.com/lxtGH/SFSegNets.

Size Wu, Wenwei Zhang, Lumin Xu et al.

Open-vocabulary dense prediction tasks including object detection and image segmentation have been advanced by the success of Contrastive Language-Image Pre-training (CLIP). CLIP models, particularly those incorporating vision transformers (ViTs), have exhibited remarkable generalization ability in zero-shot image classification. However, when transferring the vision-language alignment of CLIP from global image representation to local region representation for the open-vocabulary dense prediction tasks, CLIP ViTs suffer from the domain shift from full images to local image regions. In this paper, we embark on an in-depth analysis of the region-language alignment in CLIP models, which is essential for downstream open-vocabulary dense prediction tasks. Subsequently, we propose an approach named CLIPSelf, which adapts the image-level recognition ability of CLIP ViT to local image regions without needing any region-text pairs. CLIPSelf empowers ViTs to distill itself by aligning a region representation extracted from its dense feature map with the image-level representation of the corresponding image crop. With the enhanced CLIP ViTs, we achieve new state-of-the-art performance on open-vocabulary object detection, semantic segmentation, and panoptic segmentation across various benchmarks. Models and code are released at https://github.com/wusize/CLIPSelf.

Yue Han, Jiangning Zhang, Yabiao Wang et al.

Few-Shot Instance Segmentation (FSIS) requires detecting and segmenting novel classes with limited support examples. Existing methods based on Region Proposal Networks (RPNs) face two issues: 1) Overfitting suppresses novel class objects; 2) Dual-branch models require complex spatial correlation strategies to prevent spatial information loss when generating class prototypes. We introduce a unified framework, Reference Twice (RefT), to exploit the relationship between support and query features for FSIS and related tasks. Our three main contributions are: 1) A novel transformer-based baseline that avoids overfitting, offering a new direction for FSIS; 2) Demonstrating that support object queries encode key factors after base training, allowing query features to be enhanced twice at both feature and query levels using simple cross-attention, thus avoiding complex spatial correlation interaction; 3) Introducing a class-enhanced base knowledge distillation loss to address the issue of DETR-like models struggling with incremental settings due to the input projection layer, enabling easy extension to incremental FSIS. Extensive experimental evaluations on the COCO dataset under three FSIS settings demonstrate that our method performs favorably against existing approaches across different shots, \eg, $+8.2/+9.4$ performance gain over state-of-the-art methods with 10/30-shots. Source code and models will be available at https://github.com/hanyue1648/RefT.

Yujing Wang, Yaming Yang, Zhuo Li et al.

Attention-based neural networks, such as Transformers, have become ubiquitous in numerous applications, including computer vision, natural language processing, and time-series analysis. In all kinds of attention networks, the attention maps are crucial as they encode semantic dependencies between input tokens. However, most existing attention networks perform modeling or reasoning based on representations , wherein the attention maps of different layers are learned separately without explicit interactions. In this paper, we propose a novel and generic evolving attention mechanism, which directly models the evolution of inter-token relationships through a chain of residual convolutional modules. The major motivations are twofold. On the one hand, the attention maps in different layers share transferable knowledge, thus adding a residual connection can facilitate the information flow of inter-token relationships across layers. On the other hand, there is naturally an evolutionary trend among attention maps at different abstraction levels, so it is beneficial to exploit a dedicated convolution-based module to capture this process. Equipped with the proposed mechanism, the convolution-enhanced evolving attention networks achieve superior performance in various applications, including time-series representation, natural language understanding, machine translation, and image classification. Especially on time-series representation tasks, Evolving Attention-enhanced Dilated Convolutional (EA-DC-) Transformer outperforms state-of-the-art models significantly, achieving an average of 17% improvement compared to the best SOTA. To the best of our knowledge, this is the first work that explicitly models the layer-wise evolution of attention maps. Our implementation is available at https://github.com/pkuyym/EvolvingAttention.

Jinghao Wang, Zhengyu Wen, Xiangtai Li et al.

Panoptic Scene Graph (PSG) is a challenging task in Scene Graph Generation (SGG) that aims to create a more comprehensive scene graph representation using panoptic segmentation instead of boxes. Compared to SGG, PSG has several challenging problems: pixel-level segment outputs and full relationship exploration (It also considers thing and stuff relation). Thus, current PSG methods have limited performance, which hinders downstream tasks or applications. The goal of this work aims to design a novel and strong baseline for PSG. To achieve that, we first conduct an in-depth analysis to identify the bottleneck of the current PSG models, finding that inter-object pair-wise recall is a crucial factor that was ignored by previous PSG methods. Based on this and the recent query-based frameworks, we present a novel framework: Pair then Relation (Pair-Net), which uses a Pair Proposal Network (PPN) to learn and filter sparse pair-wise relationships between subjects and objects. Moreover, we also observed the sparse nature of object pairs for both Motivated by this, we design a lightweight Matrix Learner within the PPN, which directly learns pair-wised relationships for pair proposal generation. Through extensive ablation and analysis, our approach significantly improves upon leveraging the segmenter solid baseline. Notably, our method achieves over 10\% absolute gains compared to our baseline, PSGFormer. The code of this paper is publicly available at https://github.com/king159/Pair-Net.

Chunlei Wang, Wenquan Feng, Xiangtai Li et al.

Open-vocabulary learning has emerged as a cutting-edge research area, particularly in light of the widespread adoption of vision-based foundational models. Its primary objective is to comprehend novel concepts that are not encompassed within a predefined vocabulary. One key facet of this endeavor is Visual Grounding, which entails locating a specific region within an image based on a corresponding language description. While current foundational models excel at various visual language tasks, there's a noticeable absence of models specifically tailored for open-vocabulary visual grounding. This research endeavor introduces novel and challenging OV tasks, namely Open-Vocabulary Visual Grounding and Open-Vocabulary Phrase Localization. The overarching aim is to establish connections between language descriptions and the localization of novel objects. To facilitate this, we have curated a comprehensive annotated benchmark, encompassing 7,272 OV-VG images and 1,000 OV-PL images. In our pursuit of addressing these challenges, we delved into various baseline methodologies rooted in existing open-vocabulary object detection, VG, and phrase localization frameworks. Surprisingly, we discovered that state-of-the-art methods often falter in diverse scenarios. Consequently, we developed a novel framework that integrates two critical components: Text-Image Query Selection and Language-Guided Feature Attention. These modules are designed to bolster the recognition of novel categories and enhance the alignment between visual and linguistic information. Extensive experiments demonstrate the efficacy of our proposed framework, which consistently attains SOTA performance across the OV-VG task. Additionally, ablation studies provide further evidence of the effectiveness of our innovative models. Codes and datasets will be made publicly available at https://github.com/cv516Buaa/OV-VG.

Yibo Yang, Shixiang Chen, Xiangtai Li et al.

Modern deep neural networks for classification usually jointly learn a backbone for representation and a linear classifier to output the logit of each class. A recent study has shown a phenomenon called neural collapse that the within-class means of features and the classifier vectors converge to the vertices of a simplex equiangular tight frame (ETF) at the terminal phase of training on a balanced dataset. Since the ETF geometric structure maximally separates the pair-wise angles of all classes in the classifier, it is natural to raise the question, why do we spend an effort to learn a classifier when we know its optimal geometric structure? In this paper, we study the potential of learning a neural network for classification with the classifier randomly initialized as an ETF and fixed during training. Our analytical work based on the layer-peeled model indicates that the feature learning with a fixed ETF classifier naturally leads to the neural collapse state even when the dataset is imbalanced among classes. We further show that in this case the cross entropy (CE) loss is not necessary and can be replaced by a simple squared loss that shares the same global optimality but enjoys a better convergence property. Our experimental results show that our method is able to bring significant improvements with faster convergence on multiple imbalanced datasets.

Zhongbin Fang, Xiangtai Li, Xia Li et al.

With the rise of large-scale models trained on broad data, in-context learning has become a new learning paradigm that has demonstrated significant potential in natural language processing and computer vision tasks. Meanwhile, in-context learning is still largely unexplored in the 3D point cloud domain. Although masked modeling has been successfully applied for in-context learning in 2D vision, directly extending it to 3D point clouds remains a formidable challenge. In the case of point clouds, the tokens themselves are the point cloud positions (coordinates) that are masked during inference. Moreover, position embedding in previous works may inadvertently introduce information leakage. To address these challenges, we introduce a novel framework, named Point-In-Context, designed especially for in-context learning in 3D point clouds, where both inputs and outputs are modeled as coordinates for each task. Additionally, we propose the Joint Sampling module, carefully designed to work in tandem with the general point sampling operator, effectively resolving the aforementioned technical issues. We conduct extensive experiments to validate the versatility and adaptability of our proposed methods in handling a wide range of tasks.

Menghao Li, Chunlei Wang, Wenquan Feng et al.

Visual Grounding (VG) aims at localizing target objects from an image based on given expressions and has made significant progress with the development of detection and vision transformer. However, existing VG methods tend to generate false-alarm objects when presented with inaccurate or irrelevant descriptions, which commonly occur in practical applications. Moreover, existing methods fail to capture fine-grained features, accurate localization, and sufficient context comprehension from the whole image and textual descriptions. To address both issues, we propose an Iterative Robust Visual Grounding (IR-VG) framework with Masked Reference based Centerpoint Supervision (MRCS). The framework introduces iterative multi-level vision-language fusion (IMVF) for better alignment. We use MRCS to ahieve more accurate localization with point-wised feature supervision. Then, to improve the robustness of VG, we also present a multi-stage false-alarm sensitive decoder (MFSD) to prevent the generation of false-alarm objects when presented with inaccurate expressions. The proposed framework is evaluated on five regular VG datasets and two newly constructed robust VG datasets. Extensive experiments demonstrate that IR-VG achieves new state-of-the-art (SOTA) results, with improvements of 25\% and 10\% compared to existing SOTA approaches on the two newly proposed robust VG datasets. Moreover, the proposed framework is also verified effective on five regular VG datasets. Codes and models will be publicly at https://github.com/cv516Buaa/IR-VG.

Yu Yang, Yue Liao, Jianbiao Mei et al.

Long-horizon action-conditioned video generation aims to synthesize temporally coherent videos that follow complex action instructions over extended horizons, requiring procedural ordering, persistent action execution, and scene consistency beyond conventional TI2V's short-term fidelity. Existing single-shot video generation models typically operate in an open-loop manner, leading to incomplete action execution, hallucinated motions, and temporal drift. To address this, we propose SPIRAL, a closed-loop framework that performs sequential planning and iterative reflection for action-conditioned long-horizon video generation. Specifically, SPIRAL instantiates a think-act-reflect process: a PlanAgent decomposes high-level goals into sub-actions, which condition a VideoGenerator to synthesize each segment alongside a memory context, while a CriticAgent evaluates intermediate video segments to provide corrective feedback for iterative refinement. This closed-loop design further supports self-evolution by utilizing PlanAgent-proposed actions and CriticAgent-derived rewards for GRPO-based post-training to enhance the video generator's long-horizon consistency. Moreover, we introduce ActVideoGen-Dataset for task-specific training, and establish ActVideoGen-Bench as a dedicated evaluation suite for measuring action quality and temporal coherence. Experiments across multiple TI2V backbones alongside the self-evolving strategy show consistent gains on ActVideoGen-Bench and VBench, demonstrating the effectiveness of SPIRAL.

Jianzong Wu, Xiangtai Li, Henghui Ding et al.

In this work, we focus on open vocabulary instance segmentation to expand a segmentation model to classify and segment instance-level novel categories. Previous approaches have relied on massive caption datasets and complex pipelines to establish one-to-one mappings between image regions and words in captions. However, such methods build noisy supervision by matching non-visible words to image regions, such as adjectives and verbs. Meanwhile, context words are also important for inferring the existence of novel objects as they show high inter-correlations with novel categories. To overcome these limitations, we devise a joint \textbf{Caption Grounding and Generation (CGG)} framework, which incorporates a novel grounding loss that only focuses on matching object nouns to improve learning efficiency. We also introduce a caption generation head that enables additional supervision and contextual modeling as a complementation to the grounding loss. Our analysis and results demonstrate that grounding and generation components complement each other, significantly enhancing the segmentation performance for novel classes. Experiments on the COCO dataset with two settings: Open Vocabulary Instance Segmentation (OVIS) and Open Set Panoptic Segmentation (OSPS) demonstrate the superiority of the CGG. Specifically, CGG achieves a substantial improvement of 6.8% mAP for novel classes without extra data on the OVIS task and 15% PQ improvements for novel classes on the OSPS benchmark.

Tianmeng Yang, Jiahao Meng, Min Zhou et al.

Recent research on the robustness of Graph Neural Networks (GNNs) under noises or attacks has attracted great attention due to its importance in real-world applications. Most previous methods explore a single noise source, recovering corrupt node embedding by reliable structures bias or developing structure learning with reliable node features. However, the noises and attacks may come from both structures and features in graphs, making the graph denoising a dilemma and challenging problem. In this paper, we develop a unified graph denoising (UGD) framework to unravel the deadlock between structure and feature denoising. Specifically, a high-order neighborhood proximity evaluation method is proposed to recognize noisy edges, considering features may be perturbed simultaneously. Moreover, we propose to refine noisy features with reconstruction based on a graph auto-encoder. An iterative updating algorithm is further designed to optimize the framework and acquire a clean graph, thus enabling robust graph learning for downstream tasks. Our UGD framework is self-supervised and can be easily implemented as a plug-and-play module. We carry out extensive experiments, which proves the effectiveness and advantages of our method. Code is avalaible at https://github.com/YoungTimmy/UGD.

Jiangning Zhang, Xiangtai Li, Jian Li et al.

This paper focuses on developing modern, efficient, lightweight models for dense predictions while trading off parameters, FLOPs, and performance. Inverted Residual Block (IRB) serves as the infrastructure for lightweight CNNs, but no counterpart has been recognized by attention-based studies. This work rethinks lightweight infrastructure from efficient IRB and effective components of Transformer from a unified perspective, extending CNN-based IRB to attention-based models and abstracting a one-residual Meta Mobile Block (MMB) for lightweight model design. Following simple but effective design criterion, we deduce a modern Inverted Residual Mobile Block (iRMB) and build a ResNet-like Efficient MOdel (EMO) with only iRMB for down-stream tasks. Extensive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, e.g., EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass equal-order CNN-/Attention-based models, while trading-off the parameter, efficiency, and accuracy well: running 2.8-4.0x faster than EdgeNeXt on iPhone14.

Yibo Yang, Haobo Yuan, Xiangtai Li et al.

How to enable learnability for new classes while keeping the capability well on old classes has been a crucial challenge for class incremental learning. Beyond the normal case, long-tail class incremental learning and few-shot class incremental learning are also proposed to consider the data imbalance and data scarcity, respectively, which are common in real-world implementations and further exacerbate the well-known problem of catastrophic forgetting. Existing methods are specifically proposed for one of the three tasks. In this paper, we offer a unified solution to the misalignment dilemma in the three tasks. Concretely, we propose neural collapse terminus that is a fixed structure with the maximal equiangular inter-class separation for the whole label space. It serves as a consistent target throughout the incremental training to avoid dividing the feature space incrementally. For CIL and LTCIL, we further propose a prototype evolving scheme to drive the backbone features into our neural collapse terminus smoothly. Our method also works for FSCIL with only minor adaptations. Theoretical analysis indicates that our method holds the neural collapse optimality in an incremental fashion regardless of data imbalance or data scarcity. We also design a generalized case where we do not know the total number of classes and whether the data distribution is normal, long-tail, or few-shot for each coming session, to test the generalizability of our method. Extensive experiments with multiple datasets are conducted to demonstrate the effectiveness of our unified solution to all the three tasks and the generalized case.

Shilin Xu, Xiangtai Li, Size Wu et al.

Open-vocabulary object detection (OVOD) aims to detect the objects beyond the set of classes observed during training. This work introduces a straightforward and efficient strategy that utilizes pre-trained vision-language models (VLM), like CLIP, to identify potential novel classes through zero-shot classification. Previous methods use a class-agnostic region proposal network to detect object proposals and consider the proposals that do not match the ground truth as background. Unlike these methods, our method will select a subset of proposals that will be considered as background during the training. Then, we treat them as novel classes during training. We refer to this approach as the self-training strategy, which enhances recall and accuracy for novel classes without requiring extra annotations, datasets, and re-training. Compared to previous pseudo methods, our approach does not require re-training and offline labeling processing, which is more efficient and effective in one-shot training. Empirical evaluations on three datasets, including LVIS, V3Det, and COCO, demonstrate significant improvements over the baseline performance without incurring additional parameters or computational costs during inference. In addition, we also apply our method to various baselines. In particular, compared with the previous method, F-VLM, our method achieves a 1.7% improvement on the LVIS dataset. Combined with the recent method CLIPSelf, our method also achieves 46.7 novel class AP on COCO without introducing extra data for pertaining. We also achieve over 6.5% improvement over the F-VLM baseline in the recent challenging V3Det dataset. We release our code and models at https://github.com/xushilin1/dst-det.

Xiangtai Li, Haobo Yuan, Wenwei Zhang et al.

Video segmentation aims to segment and track every pixel in diverse scenarios accurately. In this paper, we present Tube-Link, a versatile framework that addresses multiple core tasks of video segmentation with a unified architecture. Our framework is a near-online approach that takes a short subclip as input and outputs the corresponding spatial-temporal tube masks. To enhance the modeling of cross-tube relationships, we propose an effective way to perform tube-level linking via attention along the queries. In addition, we introduce temporal contrastive learning to instance-wise discriminative features for tube-level association. Our approach offers flexibility and efficiency for both short and long video inputs, as the length of each subclip can be varied according to the needs of datasets or scenarios. Tube-Link outperforms existing specialized architectures by a significant margin on five video segmentation datasets. Specifically, it achieves almost 13% relative improvements on VIPSeg and 4% improvements on KITTI-STEP over the strong baseline Video K-Net. When using a ResNet50 backbone on Youtube-VIS-2019 and 2021, Tube-Link boosts IDOL by 3% and 4%, respectively.

Jinbin Bai, Yixuan Li, Yuchen Zhu et al.

Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion language models (dLLMs) due to their parallel decoding over the entire sequence. As a result, developing effective and efficient TTS methods to unlock dLLMs' full generative potential remains an underexplored challenge. To address this, we propose Prism (Pruning, Remasking, and Integrated Self-verification Method), an efficient TTS framework for dLLMs that (i) performs Hierarchical Trajectory Search (HTS) which dynamically prunes and reallocates compute in an early-to-mid denoising window, (ii) introduces Local branching with partial remasking to explore diverse implementations while preserving high-confidence tokens, and (iii) replaces external verifiers with Self-Verified Feedback (SVF) obtained via self-evaluation prompts on intermediate completions. Across four mathematical reasoning and code generation benchmarks on three dLLMs, including LLaDA 8B Instruct, Dream 7B Instruct, and LLaDA 2.0-mini, our Prism achieves a favorable performance-efficiency trade-off, matching best-of-N performance with substantially fewer function evaluations (NFE). The code is released at https://github.com/viiika/Prism.

Ye Tian, Ling Yang, Jiongfan Yang et al.

While thinking-aware generation aims to improve performance on complex tasks, we identify a critical failure mode where existing sequential, autoregressive approaches can paradoxically degrade performance due to error propagation. To systematically analyze this issue, we propose ParaBench, a new benchmark designed to evaluate both text and image output modalities. Our analysis using ParaBench reveals that this performance degradation is strongly correlated with poor alignment between the generated reasoning and the final image. To resolve this, we propose a parallel multimodal diffusion framework, MMaDA-Parallel, that enables continuous, bidirectional interaction between text and images throughout the entire denoising trajectory. MMaDA-Parallel is trained with supervised finetuning and then further optimized by Parallel Reinforcement Learning (ParaRL), a novel strategy that applies semantic rewards along the trajectory to enforce cross-modal consistency. Experiments validate that our model significantly improves cross-modal alignment and semantic consistency, achieving a 6.9\% improvement in Output Alignment on ParaBench compared to the state-of-the-art model, Bagel, establishing a more robust paradigm for thinking-aware image synthesis. Our code is open-sourced at https://github.com/tyfeld/MMaDA-Parallel

Shilin Xu, Xiangtai Li, Haobo Yuan et al.

The recent surge in Multimodal Large Language Models (MLLMs) has showcased their remarkable potential for achieving generalized intelligence by integrating visual understanding into Large Language Models.Nevertheless, the sheer model size of MLLMs leads to substantial memory and computational demands that hinder their widespread deployment. In this work, we do not propose a new efficient model structure or train small-scale MLLMs from scratch. Instead, we focus on what matters for training small-scale MLLMs through knowledge distillation, which is the first step from the multimodal distillation perspective. Our extensive studies involve training strategies, model choices, and distillation algorithms in the knowledge distillation process. These results show that joint alignment for both tokens and logit alignment plays critical roles in teacher-student frameworks. In addition, we draw a series of intriguing observations from this study. By evaluating different benchmarks and proper strategy, even a 2.7B small-scale model can perform on par with larger models with 7B or 13B parameters. Our code and models will be publicly available for further research.

Hao Zhou, Tiancheng Shen, Xu Yang et al.

In this paper, we highlight a problem of evaluation metrics adopted in the open-vocabulary segmentation. That is, the evaluation process still heavily relies on closed-set metrics on zero-shot or cross-dataset pipelines without considering the similarity between predicted and ground truth categories. To tackle this issue, we first survey eleven similarity measurements between two categorical words using WordNet linguistics statistics, text embedding, and language models by comprehensive quantitative analysis and user study. Built upon those explored measurements, we designed novel evaluation metrics, namely Open mIoU, Open AP, and Open PQ, tailored for three open-vocabulary segmentation tasks. We benchmarked the proposed evaluation metrics on 12 open-vocabulary methods of three segmentation tasks. Even though the relative subjectivity of similarity distance, we demonstrate that our metrics can still well evaluate the open ability of the existing open-vocabulary segmentation methods. We hope that our work can bring with the community new thinking about how to evaluate the open ability of models. The evaluation code is released in github.

Ziyu Guo, Xinyan Chen, Renrui Zhang et al.

Recent video generation models can produce high-fidelity, temporally coherent videos, indicating that they may encode substantial world knowledge. Beyond realistic synthesis, they also exhibit emerging behaviors indicative of visual perception, modeling, and manipulation. Yet, an important question still remains: Are video models ready to serve as zero-shot reasoners in challenging visual reasoning scenarios? In this work, we conduct an empirical study to comprehensively investigate this question, focusing on the leading and popular Veo-3. We evaluate its reasoning behavior across 12 dimensions, including spatial, geometric, physical, temporal, and embodied logic, systematically characterizing both its strengths and failure modes. To standardize this study, we curate the evaluation data into MME-CoF, a compact benchmark that enables in-depth and thorough assessment of Chain-of-Frame (CoF) reasoning. Our findings reveal that while current video models demonstrate promising reasoning patterns on short-horizon spatial coherence, fine-grained grounding, and locally consistent dynamics, they remain limited in long-horizon causal reasoning, strict geometric constraints, and abstract logic. Overall, they are not yet reliable as standalone zero-shot reasoners, but exhibit encouraging signs as complementary visual engines alongside dedicated reasoning models. Project page: https://video-cof.github.io

Haobo Yuan, Xiangtai Li, Tao Zhang et al.

This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, which are often limited to specific modalities and tasks, Sa2VA supports a wide range of image and video tasks, including referring segmentation and conversation, with minimal one-shot instruction tuning. Sa2VA combines SAM-2, a foundation video segmentation model, with MLLM, the advanced vision-language model, and unifies text, image, and video into a shared LLM token space. Using the LLM, Sa2VA generates instruction tokens that guide SAM-2 in producing precise masks, enabling a grounded, multi-modal understanding of both static and dynamic visual content. Additionally, we introduce Ref-SAV, an auto-labeled dataset containing over 72k object expressions in complex video scenes, designed to boost model performance. We also manually validate 2k video objects in the Ref-SAV datasets to benchmark referring video object segmentation in complex environments. Experiments show that Sa2VA achieves strong performance across multiple tasks, particularly in referring video object segmentation, highlighting its potential for complex real-world applications. In addition, Sa2VA can be easily extended into various VLMs, including Qwen-VL and Intern-VL, which can be updated with rapid process in current open-sourced VLMs. Code and models have been provided to the community.

Xiangyu Zhao, Yicheng Chen, Shilin Xu et al.

Grounding-DINO is a state-of-the-art open-set detection model that tackles multiple vision tasks including Open-Vocabulary Detection (OVD), Phrase Grounding (PG), and Referring Expression Comprehension (REC). Its effectiveness has led to its widespread adoption as a mainstream architecture for various downstream applications. However, despite its significance, the original Grounding-DINO model lacks comprehensive public technical details due to the unavailability of its training code. To bridge this gap, we present MM-Grounding-DINO, an open-source, comprehensive, and user-friendly baseline, which is built with the MMDetection toolbox. It adopts abundant vision datasets for pre-training and various detection and grounding datasets for fine-tuning. We give a comprehensive analysis of each reported result and detailed settings for reproduction. The extensive experiments on the benchmarks mentioned demonstrate that our MM-Grounding-DINO-Tiny outperforms the Grounding-DINO-Tiny baseline. We release all our models to the research community. Codes and trained models are released at https://github.com/open-mmlab/mmdetection/tree/main/configs/mm_grounding_dino.

Shengqiong Wu, Bobo Li, Xinkai Wang et al.

Unified Vision-Language Models (UVLMs) aim to advance multimodal learning by supporting both understanding and generation within a single framework. However, existing approaches largely focus on architectural unification while overlooking the need for explicit interaction between the two capabilities during task solving. As a result, current models treat understanding and generation as parallel skills rather than synergistic processes. To achieve real synergy, we introduce the interleaved Analyzing-Drafting problem-solving loop (AD-Loop), a new think paradigm that dynamically alternates between analytic and drafting operations. By interleaving textual thoughts with visual thoughts, AD-Loop enables models to iteratively refine both comprehension and outputs, fostering genuine synergy. To train this mechanism, we design a two-stage strategy: supervised learning on interleaved thought data to initialize alternation, followed by reinforcement learning to promote adaptive and autonomous control. Extensive experiments demonstrate that AD-Loop consistently improves performance across standard benchmarks for both understanding and generation, with strong transferability to various UVLMs architectures. Visual analyses further validate the effectiveness of implicit visual thoughts. These results highlight AD-Loop as a principled and broadly applicable strategy for synergizing comprehension and creation. The project page is at https://sqwu.top/AD-Loop.

Peng Lu, Tao Jiang, Yining Li et al.

Real-time multi-person pose estimation presents significant challenges in balancing speed and precision. While two-stage top-down methods slow down as the number of people in the image increases, existing one-stage methods often fail to simultaneously deliver high accuracy and real-time performance. This paper introduces RTMO, a one-stage pose estimation framework that seamlessly integrates coordinate classification by representing keypoints using dual 1-D heatmaps within the YOLO architecture, achieving accuracy comparable to top-down methods while maintaining high speed. We propose a dynamic coordinate classifier and a tailored loss function for heatmap learning, specifically designed to address the incompatibilities between coordinate classification and dense prediction models. RTMO outperforms state-of-the-art one-stage pose estimators, achieving 1.1% higher AP on COCO while operating about 9 times faster with the same backbone. Our largest model, RTMO-l, attains 74.8% AP on COCO val2017 and 141 FPS on a single V100 GPU, demonstrating its efficiency and accuracy. The code and models are available at https://github.com/open-mmlab/mmpose/tree/main/projects/rtmo.

Jiangning Zhang, Xuhai Chen, Yabiao Wang et al.

This work studies a challenging and practical issue known as multi-class unsupervised anomaly detection (MUAD). This problem requires only normal images for training while simultaneously testing both normal and anomaly images across multiple classes. Existing reconstruction-based methods typically adopt pyramidal networks as encoders and decoders to obtain multi-resolution features, often involving complex sub-modules with extensive handcraft engineering. In contrast, a plain Vision Transformer (ViT) showcasing a more straightforward architecture has proven effective in multiple domains, including detection and segmentation tasks. It is simpler, more effective, and elegant. Following this spirit, we explore the use of only plain ViT features for MUAD. We first abstract a Meta-AD concept by synthesizing current reconstruction-based methods. Subsequently, we instantiate a novel ViT-based ViTAD structure, designed incrementally from both global and local perspectives. This model provide a strong baseline to facilitate future research. Additionally, this paper uncovers several intriguing findings for further investigation. Finally, we comprehensively and fairly benchmark various approaches using eight metrics. Utilizing a basic training regimen with only an MSE loss, ViTAD achieves state-of-the-art results and efficiency on MVTec AD, VisA, and Uni-Medical datasets. \Eg, achieving 85.4 mAD that surpasses UniAD by +3.0 for the MVTec AD dataset, and it requires only 1.1 hours and 2.3G GPU memory to complete model training on a single V100 that can serve as a strong baseline to facilitate the development of future research. Full code is available at https://zhangzjn.github.io/projects/ViTAD/.

Yue Han, Junwei Zhu, Yuxiang Feng et al.

Current diffusion-based face animation methods generally adopt a ReferenceNet (a copy of U-Net) and a large amount of curated self-acquired data to learn appearance features, as robust appearance features are vital for ensuring temporal stability. However, when trained on public datasets, the results often exhibit a noticeable performance gap in image quality and temporal consistency. To address this issue, we meticulously examine the essential appearance features in the facial animation tasks, which include motion-agnostic (e.g., clothing, background) and motion-related (e.g., facial details) texture components, along with high-level discriminative identity features. Drawing from this analysis, we introduce a Motion-Identity Modulated Appearance Learning Module (MIA) that modulates CLIP features at both motion and identity levels. Additionally, to tackle the semantic/ color discontinuities between clips, we design an Inter-clip Affinity Learning Module (ICA) to model temporal relationships across clips. Our method achieves precise facial motion control (i.e., expressions and gaze), faithful identity preservation, and generates animation videos that maintain both intra/inter-clip temporal consistency. Moreover, it easily adapts to various modalities of driving sources. Extensive experiments demonstrate the superiority of our method.

Yiran Song, Qianyu Zhou, Xiangtai Li et al.

In this paper, we address the challenge of image resolution variation for the Segment Anything Model (SAM). SAM, known for its zero-shot generalizability, exhibits a performance degradation when faced with datasets with varying image sizes. Previous approaches tend to resize the image to a fixed size or adopt structure modifications, hindering the preservation of SAM's rich prior knowledge. Besides, such task-specific tuning necessitates a complete retraining of the model, which is cost-expensive and unacceptable for deployment in the downstream tasks. In this paper, we reformulate this issue as a length extrapolation problem, where token sequence length varies while maintaining a consistent patch size for images of different sizes. To this end, we propose Scalable Bias-Mode Attention Mask (BA-SAM) to enhance SAM's adaptability to varying image resolutions while eliminating the need for structure modifications. Firstly, we introduce a new scaling factor to ensure consistent magnitude in the attention layer's dot product values when the token sequence length changes. Secondly, we present a bias-mode attention mask that allows each token to prioritize neighboring information, mitigating the impact of untrained distant information. Our BA-SAM demonstrates efficacy in two scenarios: zero-shot and fine-tuning. Extensive evaluation on diverse datasets, including DIS5K, DUTS, ISIC, COD10K, and COCO, reveals its ability to significantly mitigate performance degradation in the zero-shot setting and achieve state-of-the-art performance with minimal fine-tuning. Furthermore, we propose a generalized model and benchmark, showcasing BA-SAM's generalizability across all four datasets simultaneously. Code is available at https://github.com/zongzi13545329/BA-SAM

Yikang Zhou, Tao Zhang, Dengxian Gong et al.

Pixel-wise capabilities are essential for building interactive intelligent systems. However, pixel-wise multi-modal LLMs (MLLMs) remain difficult to scale due to complex region-level encoders, specialized segmentation decoders, and incompatible training objectives. To address these challenges, we present SAMTok, a discrete mask tokenizer that converts any region mask into two special tokens and reconstructs the mask using these tokens with high fidelity. By treating masks as new language tokens, SAMTok enables base MLLMs (such as the QwenVL series) to learn pixel-wise capabilities through standard next-token prediction and simple reinforcement learning, without architectural modifications and specialized loss design. SAMTok builds on SAM2 and is trained on 209M diverse masks using a mask encoder and residual vector quantizer to produce discrete, compact, and information-rich tokens. With 5M SAMTok-formatted mask understanding and generation data samples, QwenVL-SAMTok attains state-of-the-art or comparable results on region captioning, region VQA, grounded conversation, referring segmentation, scene graph parsing, and multi-round interactive segmentation. We further introduce a textual answer-matching reward that enables efficient reinforcement learning for mask generation, delivering substantial improvements on GRES and GCG benchmarks. Our results demonstrate a scalable and straightforward paradigm for equipping MLLMs with strong pixel-wise capabilities. Our code and models are available.

Jinbin Bai, Wei Chow, Ling Yang et al.

We present HumanEdit, a high-quality, human-rewarded dataset specifically designed for instruction-guided image editing, enabling precise and diverse image manipulations through open-form language instructions. Previous large-scale editing datasets often incorporate minimal human feedback, leading to challenges in aligning datasets with human preferences. HumanEdit bridges this gap by employing human annotators to construct data pairs and administrators to provide feedback. With meticulously curation, HumanEdit comprises 5,751 images and requires more than 2,500 hours of human effort across four stages, ensuring both accuracy and reliability for a wide range of image editing tasks. The dataset includes six distinct types of editing instructions: Action, Add, Counting, Relation, Remove, and Replace, encompassing a broad spectrum of real-world scenarios. All images in the dataset are accompanied by masks, and for a subset of the data, we ensure that the instructions are sufficiently detailed to support mask-free editing. Furthermore, HumanEdit offers comprehensive diversity and high-resolution $1024 \times 1024$ content sourced from various domains, setting a new versatile benchmark for instructional image editing datasets. With the aim of advancing future research and establishing evaluation benchmarks in the field of image editing, we release HumanEdit at https://huggingface.co/datasets/BryanW/HumanEdit.

Yikang Zhou, Tao Zhang, Shunping Ji et al.

Modern video segmentation methods adopt object queries to perform inter-frame association and demonstrate satisfactory performance in tracking continuously appearing objects despite large-scale motion and transient occlusion. However, they all underperform on newly emerging and disappearing objects that are common in the real world because they attempt to model object emergence and disappearance through feature transitions between background and foreground queries that have significant feature gaps. We introduce Dynamic Anchor Queries (DAQ) to shorten the transition gap between the anchor and target queries by dynamically generating anchor queries based on the features of potential candidates. Furthermore, we introduce a query-level object Emergence and Disappearance Simulation (EDS) strategy, which unleashes DAQ's potential without any additional cost. Finally, we combine our proposed DAQ and EDS with DVIS to obtain DVIS-DAQ. Extensive experiments demonstrate that DVIS-DAQ achieves a new state-of-the-art (SOTA) performance on five mainstream video segmentation benchmarks. Code and models are available at \url{https://github.com/SkyworkAI/DAQ-VS}.

Shaocong Long, Qianyu Zhou, Xiangtai Li et al.

Domain generalization~(DG) aims at solving distribution shift problems in various scenes. Existing approaches are based on Convolution Neural Networks (CNNs) or Vision Transformers (ViTs), which suffer from limited receptive fields or quadratic complexities issues. Mamba, as an emerging state space model (SSM), possesses superior linear complexity and global receptive fields. Despite this, it can hardly be applied to DG to address distribution shifts, due to the hidden state issues and inappropriate scan mechanisms. In this paper, we propose a novel framework for DG, named DGMamba, that excels in strong generalizability toward unseen domains and meanwhile has the advantages of global receptive fields, and efficient linear complexity. Our DGMamba compromises two core components: Hidden State Suppressing~(HSS) and Semantic-aware Patch refining~(SPR). In particular, HSS is introduced to mitigate the influence of hidden states associated with domain-specific features during output prediction. SPR strives to encourage the model to concentrate more on objects rather than context, consisting of two designs: Prior-Free Scanning~(PFS), and Domain Context Interchange~(DCI). Concretely, PFS aims to shuffle the non-semantic patches within images, creating more flexible and effective sequences from images, and DCI is designed to regularize Mamba with the combination of mismatched non-semantic and semantic information by fusing patches among domains. Extensive experiments on five commonly used DG benchmarks demonstrate that the proposed DGMamba achieves remarkably superior results to state-of-the-art models. The code will be made publicly available at https://github.com/longshaocong/DGMamba.

Tao Zhang, Xiangtai Li, Zilong Huang et al.

Multimodal Large Language Models (MLLMs) achieve remarkable performance for fine-grained pixel-level understanding tasks. However, all the works rely heavily on extra components, such as vision encoder (CLIP), segmentation experts, leading to high system complexity and limiting model scaling. In this work, our goal is to explore a highly simplified MLLM without introducing extra components. Our work is motivated by the recent works on Single trAnsformer as a unified vIsion-Language Model (SAIL) design, where these works jointly learn vision tokens and text tokens in transformers. We present Pixel-SAIL, a single transformer for pixel-wise MLLM tasks. In particular, we present three technical improvements on the plain baseline. First, we design a learnable upsampling module to refine visual token features. Secondly, we propose a novel visual prompt injection strategy to enable the single transformer to understand visual prompt inputs and benefit from the early fusion of visual prompt embeddings and vision tokens. Thirdly, we introduce a vision expert distillation strategy to efficiently enhance the single transformer's fine-grained feature extraction capability. In addition, we have collected a comprehensive pixel understanding benchmark (PerBench), using a manual check. It includes three tasks: detailed object description, visual prompt-based question answering, and visual-text referring segmentation. Extensive experiments on four referring segmentation benchmarks, one visual prompt benchmark, and our PerBench show that our Pixel-SAIL achieves comparable or even better results with a much simpler pipeline. Code and model will be released at https://github.com/magic-research/Sa2VA.

Weixian Lei, Jiacong Wang, Haochen Wang et al.

This paper introduces SAIL, a single transformer unified multimodal large language model (MLLM) that integrates raw pixel encoding and language decoding within a singular architecture. Unlike existing modular MLLMs, which rely on a pre-trained vision transformer (ViT), SAIL eliminates the need for a separate vision encoder, presenting a more minimalist architecture design. Instead of introducing novel architectural components, SAIL adapts mix-attention mechanisms and multimodal positional encodings to better align with the distinct characteristics of visual and textual modalities. We systematically compare SAIL's properties-including scalability, cross-modal information flow patterns, and visual representation capabilities-with those of modular MLLMs. By scaling both training data and model size, SAIL achieves performance comparable to modular MLLMs. Notably, the removal of pretrained ViT components enhances SAIL's scalability and results in significantly different cross-modal information flow patterns. Moreover, SAIL demonstrates strong visual representation capabilities, achieving results on par with ViT-22B in vision tasks such as semantic segmentation. Code and models are available at https://github.com/bytedance/SAIL.

Sixiang Chen, Jinbin Bai, Zhuoran Zhao et al.

The landscape of image generation has rapidly evolved, from early GAN-based approaches to diffusion models and, most recently, to unified generative architectures that seek to bridge understanding and generation tasks. Recent advances, especially the GPT-4o, have demonstrated the feasibility of high-fidelity multimodal generation, their architectural design remains mysterious and unpublished. This prompts the question of whether image and text generation have already been successfully integrated into a unified framework for those methods. In this work, we conduct an empirical study of GPT-4o's image generation capabilities, benchmarking it against leading open-source and commercial models. Our evaluation covers four main categories, including text-to-image, image-to-image, image-to-3D, and image-to-X generation, with more than 20 tasks. Our analysis highlights the strengths and limitations of GPT-4o under various settings, and situates it within the broader evolution of generative modeling. Through this investigation, we identify promising directions for future unified generative models, emphasizing the role of architectural design and data scaling. For a high-definition version of the PDF, please refer to the link on GitHub: \href{https://github.com/Ephemeral182/Empirical-Study-of-GPT-4o-Image-Gen}{https://github.com/Ephemeral182/Empirical-Study-of-GPT-4o-Image-Gen}.

Ao Liang, Lingdong Kong, Tianyi Yan et al.

Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. Despite rapid progress, the field still lacks a unified way to assess whether generated worlds preserve geometry, obey physics, or support reliable control. We introduce WorldLens, a full-spectrum benchmark evaluating how well a model builds, understands, and behaves within its generated world. It spans five aspects -- Generation, Reconstruction, Action-Following, Downstream Task, and Human Preference -- jointly covering visual realism, geometric consistency, physical plausibility, and functional reliability. Across these dimensions, no existing world model excels universally: those with strong textures often violate physics, while geometry-stable ones lack behavioral fidelity. To align objective metrics with human judgment, we further construct WorldLens-26K, a large-scale dataset of human-annotated videos with numerical scores and textual rationales, and develop WorldLens-Agent, an evaluation model distilled from these annotations to enable scalable, explainable scoring. Together, the benchmark, dataset, and agent form a unified ecosystem for measuring world fidelity -- standardizing how future models are judged not only by how real they look, but by how real they behave.

Yue Han, Jiangning Zhang, Junwei Zhu et al.

This work presents FaceX framework, a novel facial generalist model capable of handling diverse facial tasks simultaneously. To achieve this goal, we initially formulate a unified facial representation for a broad spectrum of facial editing tasks, which macroscopically decomposes a face into fundamental identity, intra-personal variation, and environmental factors. Based on this, we introduce Facial Omni-Representation Decomposing (FORD) for seamless manipulation of various facial components, microscopically decomposing the core aspects of most facial editing tasks. Furthermore, by leveraging the prior of a pretrained StableDiffusion (SD) to enhance generation quality and accelerate training, we design Facial Omni-Representation Steering (FORS) to first assemble unified facial representations and then effectively steer the SD-aware generation process by the efficient Facial Representation Controller (FRC). %Without any additional features, Our versatile FaceX achieves competitive performance compared to elaborate task-specific models on popular facial editing tasks. Full codes and models will be available at https://github.com/diffusion-facex/FaceX.

Hao Yang, Qianyu Zhou, Haijia Sun et al.

Domain Generalization (DG) has been recently explored to improve the generalizability of point cloud classification (PCC) models toward unseen domains. However, they often suffer from limited receptive fields or quadratic complexity due to using convolution neural networks or vision Transformers. In this paper, we present the first work that studies the generalizability of state space models (SSMs) in DG PCC and find that directly applying SSMs into DG PCC will encounter several challenges: the inherent topology of the point cloud tends to be disrupted and leads to noise accumulation during the serialization stage. Besides, the lack of designs in domain-agnostic feature learning and data scanning will introduce unanticipated domain-specific information into the 3D sequence data. To this end, we propose a novel framework, PointDGMamba, that excels in strong generalizability toward unseen domains and has the advantages of global receptive fields and efficient linear complexity. PointDGMamba consists of three innovative components: Masked Sequence Denoising (MSD), Sequence-wise Cross-domain Feature Aggregation (SCFA), and Dual-level Domain Scanning (DDS). In particular, MSD selectively masks out the noised point tokens of the point cloud sequences, SCFA introduces cross-domain but same-class point cloud features to encourage the model to learn how to extract more generalized features. DDS includes intra-domain scanning and cross-domain scanning to facilitate information exchange between features. In addition, we propose a new and more challenging benchmark PointDG-3to1 for multi-domain generalization. Extensive experiments demonstrate the effectiveness and state-of-the-art performance of PointDGMamba.