Huchuan Lu

Yichen Yuan, Yifan Wang, Lijun Wang et al. · stanford

Recent leading zero-shot video object segmentation (ZVOS) works devote to integrating appearance and motion information by elaborately designing feature fusion modules and identically applying them in multiple feature stages. Our preliminary experiments show that with the strong long-range dependency modeling capacity of Transformer, simply concatenating the two modality features and feeding them to vanilla Transformers for feature fusion can distinctly benefit the performance but at a cost of heavy computation. Through further empirical analysis, we find that attention dependencies learned in Transformer in different stages exhibit completely different properties: global query-independent dependency in the low-level stages and semantic-specific dependency in the high-level stages. Motivated by the observations, we propose two Transformer variants: i) Context-Sharing Transformer (CST) that learns the global-shared contextual information within image frames with a lightweight computation. ii) Semantic Gathering-Scattering Transformer (SGST) that models the semantic correlation separately for the foreground and background and reduces the computation cost with a soft token merging mechanism. We apply CST and SGST for low-level and high-level feature fusions, respectively, formulating a level-isomerous Transformer framework for ZVOS task. Compared with the baseline that uses vanilla Transformers for multi-stage fusion, ours significantly increase the speed by 13 times and achieves new state-of-the-art ZVOS performance. Code is available at https://github.com/DLUT-yyc/Isomer.

Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang et al.

The recently proposed camouflaged object detection (COD) attempts to segment objects that are visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Apart from high intrinsic similarity between the camouflaged objects and their background, the objects are usually diverse in scale, fuzzy in appearance, and even severely occluded. To deal with these problems, we propose a mixed-scale triplet network, \textbf{ZoomNet}, which mimics the behavior of humans when observing vague images, i.e., zooming in and out. Specifically, our ZoomNet employs the zoom strategy to learn the discriminative mixed-scale semantics by the designed scale integration unit and hierarchical mixed-scale unit, which fully explores imperceptible clues between the candidate objects and background surroundings. Moreover, considering the uncertainty and ambiguity derived from indistinguishable textures, we construct a simple yet effective regularization constraint, uncertainty-aware loss, to promote the model to accurately produce predictions with higher confidence in candidate regions. Without bells and whistles, our proposed highly task-friendly model consistently surpasses the existing 23 state-of-the-art methods on four public datasets. Besides, the superior performance over the recent cutting-edge models on the SOD task also verifies the effectiveness and generality of our model. The code will be available at \url{https://github.com/lartpang/ZoomNet}.

Jiawen Zhu, Simiao Lai, Xin Chen et al.

Visible-modal object tracking gives rise to a series of downstream multi-modal tracking tributaries. To inherit the powerful representations of the foundation model, a natural modus operandi for multi-modal tracking is full fine-tuning on the RGB-based parameters. Albeit effective, this manner is not optimal due to the scarcity of downstream data and poor transferability, etc. In this paper, inspired by the recent success of the prompt learning in language models, we develop Visual Prompt multi-modal Tracking (ViPT), which learns the modal-relevant prompts to adapt the frozen pre-trained foundation model to various downstream multimodal tracking tasks. ViPT finds a better way to stimulate the knowledge of the RGB-based model that is pre-trained at scale, meanwhile only introducing a few trainable parameters (less than 1% of model parameters). ViPT outperforms the full fine-tuning paradigm on multiple downstream tracking tasks including RGB+Depth, RGB+Thermal, and RGB+Event tracking. Extensive experiments show the potential of visual prompt learning for multi-modal tracking, and ViPT can achieve state-of-the-art performance while satisfying parameter efficiency. Code and models are available at https://github.com/jiawen-zhu/ViPT.

Bin Yan, Yi Jiang, Jiannan Wu et al.

All instance perception tasks aim at finding certain objects specified by some queries such as category names, language expressions, and target annotations, but this complete field has been split into multiple independent subtasks. In this work, we present a universal instance perception model of the next generation, termed UNINEXT. UNINEXT reformulates diverse instance perception tasks into a unified object discovery and retrieval paradigm and can flexibly perceive different types of objects by simply changing the input prompts. This unified formulation brings the following benefits: (1) enormous data from different tasks and label vocabularies can be exploited for jointly training general instance-level representations, which is especially beneficial for tasks lacking in training data. (2) the unified model is parameter-efficient and can save redundant computation when handling multiple tasks simultaneously. UNINEXT shows superior performance on 20 challenging benchmarks from 10 instance-level tasks including classical image-level tasks (object detection and instance segmentation), vision-and-language tasks (referring expression comprehension and segmentation), and six video-level object tracking tasks. Code is available at https://github.com/MasterBin-IIAU/UNINEXT.

Bin Yan, Yi Jiang, Peize Sun et al.

We present a unified method, termed Unicorn, that can simultaneously solve four tracking problems (SOT, MOT, VOS, MOTS) with a single network using the same model parameters. Due to the fragmented definitions of the object tracking problem itself, most existing trackers are developed to address a single or part of tasks and overspecialize on the characteristics of specific tasks. By contrast, Unicorn provides a unified solution, adopting the same input, backbone, embedding, and head across all tracking tasks. For the first time, we accomplish the great unification of the tracking network architecture and learning paradigm. Unicorn performs on-par or better than its task-specific counterparts in 8 tracking datasets, including LaSOT, TrackingNet, MOT17, BDD100K, DAVIS16-17, MOTS20, and BDD100K MOTS. We believe that Unicorn will serve as a solid step towards the general vision model. Code is available at https://github.com/MasterBin-IIAU/Unicorn.

Mingzhan Yang, Guangxin Han, Bin Yan et al.

Multi-Object Tracking (MOT) aims to detect and associate all desired objects across frames. Most methods accomplish the task by explicitly or implicitly leveraging strong cues (i.e., spatial and appearance information), which exhibit powerful instance-level discrimination. However, when object occlusion and clustering occur, spatial and appearance information will become ambiguous simultaneously due to the high overlap among objects. In this paper, we demonstrate this long-standing challenge in MOT can be efficiently and effectively resolved by incorporating weak cues to compensate for strong cues. Along with velocity direction, we introduce the confidence and height state as potential weak cues. With superior performance, our method still maintains Simple, Online and Real-Time (SORT) characteristics. Also, our method shows strong generalization for diverse trackers and scenarios in a plug-and-play and training-free manner. Significant and consistent improvements are observed when applying our method to 5 different representative trackers. Further, with both strong and weak cues, our method Hybrid-SORT achieves superior performance on diverse benchmarks, including MOT17, MOT20, and especially DanceTrack where interaction and severe occlusion frequently happen with complex motions. The code and models are available at https://github.com/ymzis69/HybridSORT.

Jiawen Zhu, Huayi Tang, Zhi-Qi Cheng et al. · cmu, uw

Existing nighttime unmanned aerial vehicle (UAV) trackers follow an "Enhance-then-Track" architecture - first using a light enhancer to brighten the nighttime video, then employing a daytime tracker to locate the object. This separate enhancement and tracking fails to build an end-to-end trainable vision system. To address this, we propose a novel architecture called Darkness Clue-Prompted Tracking (DCPT) that achieves robust UAV tracking at night by efficiently learning to generate darkness clue prompts. Without a separate enhancer, DCPT directly encodes anti-dark capabilities into prompts using a darkness clue prompter (DCP). Specifically, DCP iteratively learns emphasizing and undermining projections for darkness clues. It then injects these learned visual prompts into a daytime tracker with fixed parameters across transformer layers. Moreover, a gated feature aggregation mechanism enables adaptive fusion between prompts and between prompts and the base model. Extensive experiments show state-of-the-art performance for DCPT on multiple dark scenario benchmarks. The unified end-to-end learning of enhancement and tracking in DCPT enables a more trainable system. The darkness clue prompting efficiently injects anti-dark knowledge without extra modules. Code is available at https://github.com/bearyi26/DCPT.

Xin Chen, Ben Kang, Dong Wang et al.

In recent years, target tracking has made great progress in accuracy. This development is mainly attributed to powerful networks (such as transformers) and additional modules (such as online update and refinement modules). However, less attention has been paid to tracking speed. Most state-of-the-art trackers are satisfied with the real-time speed on powerful GPUs. However, practical applications necessitate higher requirements for tracking speed, especially when edge platforms with limited resources are used. In this work, we present an efficient tracking method via a hierarchical cross-attention transformer named HCAT. Our model runs about 195 fps on GPU, 45 fps on CPU, and 55 fps on the edge AI platform of NVidia Jetson AGX Xavier. Experiments show that our HCAT achieves promising results on LaSOT, GOT-10k, TrackingNet, NFS, OTB100, UAV123, and VOT2020. Code and models are available at https://github.com/chenxin-dlut/HCAT.

Xin Chen, Bin Yan, Jiawen Zhu et al.

Correlation has a critical role in the tracking field, especially in recent popular Siamese-based trackers. The correlation operation is a simple fusion method that considers the similarity between the template and the search region. However, the correlation operation is a local linear matching process, losing semantic information and easily falling into a local optimum, which may be the bottleneck in designing high-accuracy tracking algorithms. In this work, to determine whether a better feature fusion method exists than correlation, a novel attention-based feature fusion network, inspired by the transformer, is presented. This network effectively combines the template and search region features using attention. Specifically, the proposed method includes an ego-context augment module based on self-attention and a cross-feature augment module based on cross-attention. First, we present a transformer tracking (named TransT) method based on the Siamese-like feature extraction backbone, the designed attention-based fusion mechanism, and the classification and regression head. Based on the TransT baseline, we further design a segmentation branch to generate an accurate mask. Finally, we propose a stronger version of TransT by extending TransT with a multi-template scheme and an IoU prediction head, named TransT-M. Experiments show that our TransT and TransT-M methods achieve promising results on seven popular datasets. Code and models are available at https://github.com/chenxin-dlut/TransT-M.

Xiaoqi Zhao, Hongpeng Jia, Youwei Pang et al.

Accurate medical image segmentation is critical for early medical diagnosis. Most existing methods are based on U-shape structure and use element-wise addition or concatenation to fuse different level features progressively in decoder. However, both the two operations easily generate plenty of redundant information, which will weaken the complementarity between different level features, resulting in inaccurate localization and blurred edges of lesions. To address this challenge, we propose a general multi-scale in multi-scale subtraction network (M$^{2}$SNet) to finish diverse segmentation from medical image. Specifically, we first design a basic subtraction unit (SU) to produce the difference features between adjacent levels in encoder. Next, we expand the single-scale SU to the intra-layer multi-scale SU, which can provide the decoder with both pixel-level and structure-level difference information. Then, we pyramidally equip the multi-scale SUs at different levels with varying receptive fields, thereby achieving the inter-layer multi-scale feature aggregation and obtaining rich multi-scale difference information. In addition, we build a training-free network ``LossNet'' to comprehensively supervise the task-aware features from bottom layer to top layer, which drives our multi-scale subtraction network to capture the detailed and structural cues simultaneously. Without bells and whistles, our method performs favorably against most state-of-the-art methods under different evaluation metrics on eleven datasets of four different medical image segmentation tasks of diverse image modalities, including color colonoscopy imaging, ultrasound imaging, computed tomography (CT), and optical coherence tomography (OCT). The source code can be available at https://github.com/Xiaoqi-Zhao-DLUT/MSNet.

Xiaoqi Zhao, Youwei Pang, Lihe Zhang et al.

Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extracting salient objects in complex environments. However, high-quality depth sensors are expensive and can not be widely applied. While general depth sensors produce the noisy and sparse depth information, which brings the depth-based networks with irreversible interference. In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD). Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. In this way, the depth information can be completed and purified. Moreover, we introduce a multi-modal filtered transformer (MFT) module, which equips with three modality-specific filters to generate the transformer-enhanced feature for each modality. The proposed model works in a depth-free style during the testing phase. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time. And, the resulted depth map can help existing RGB-D SOD methods obtain significant performance gain. The source code will be publicly available at https://github.com/Xiaoqi-Zhao-DLUT/MMFT.

Xinhao Deng, Pingping Zhang, Wei Liu et al.

Salient Object Detection (SOD) aims to identify and segment the most conspicuous objects in an image or video. As an important pre-processing step, it has many potential applications in multimedia and vision tasks. With the advance of imaging devices, SOD with high-resolution images is of great demand, recently. However, traditional SOD methods are largely limited to low-resolution images, making them difficult to adapt to the development of High-Resolution SOD (HRSOD). Although some HRSOD methods emerge, there are no large enough datasets for training and evaluating. Besides, current HRSOD methods generally produce incomplete object regions and irregular object boundaries. To address above issues, in this work, we first propose a new HRS10K dataset, which contains 10,500 high-quality annotated images at 2K-8K resolution. As far as we know, it is the largest dataset for the HRSOD task, which will significantly help future works in training and evaluating models. Furthermore, to improve the HRSOD performance, we propose a novel Recurrent Multi-scale Transformer (RMFormer), which recurrently utilizes shared Transformers and multi-scale refinement architectures. Thus, high-resolution saliency maps can be generated with the guidance of lower-resolution predictions. Extensive experiments on both high-resolution and low-resolution benchmarks show the effectiveness and superiority of the proposed framework. The source code and dataset are released at: https://github.com/DrowsyMon/RMFormer.

Haiwen Diao, Ying Zhang, Wei Liu et al.

Exploiting fine-grained correspondence and visual-semantic alignments has shown great potential in image-text matching. Generally, recent approaches first employ a cross-modal attention unit to capture latent region-word interactions, and then integrate all the alignments to obtain the final similarity. However, most of them adopt one-time forward association or aggregation strategies with complex architectures or additional information, while ignoring the regulation ability of network feedback. In this paper, we develop two simple but quite effective regulators which efficiently encode the message output to automatically contextualize and aggregate cross-modal representations. Specifically, we propose (i) a Recurrent Correspondence Regulator (RCR) which facilitates the cross-modal attention unit progressively with adaptive attention factors to capture more flexible correspondence, and (ii) a Recurrent Aggregation Regulator (RAR) which adjusts the aggregation weights repeatedly to increasingly emphasize important alignments and dilute unimportant ones. Besides, it is interesting that RCR and RAR are plug-and-play: both of them can be incorporated into many frameworks based on cross-modal interaction to obtain significant benefits, and their cooperation achieves further improvements. Extensive experiments on MSCOCO and Flickr30K datasets validate that they can bring an impressive and consistent R@1 gain on multiple models, confirming the general effectiveness and generalization ability of the proposed methods. Code and pre-trained models are available at: https://github.com/Paranioar/RCAR.

Xin Chen, Ben Kang, Jiawen Zhu et al.

In this paper, we introduce a new sequence-to-sequence learning framework for RGB-based and multi-modal object tracking. First, we present SeqTrack for RGB-based tracking. It casts visual tracking as a sequence generation task, forecasting object bounding boxes in an autoregressive manner. This differs from previous trackers, which depend on the design of intricate head networks, such as classification and regression heads. SeqTrack employs a basic encoder-decoder transformer architecture. The encoder utilizes a bidirectional transformer for feature extraction, while the decoder generates bounding box sequences autoregressively using a causal transformer. The loss function is a plain cross-entropy. Second, we introduce SeqTrackv2, a unified sequence-to-sequence framework for multi-modal tracking tasks. Expanding upon SeqTrack, SeqTrackv2 integrates a unified interface for auxiliary modalities and a set of task-prompt tokens to specify the task. This enables it to manage multi-modal tracking tasks using a unified model and parameter set. This sequence learning paradigm not only simplifies the tracking framework, but also showcases superior performance across 14 challenging benchmarks spanning five single- and multi-modal tracking tasks. The code and models are available at https://github.com/chenxin-dlut/SeqTrackv2.

Haiwen Diao, Bo Wan, Ying Zhang et al.

Parameter-efficient transfer learning (PETL), i.e., fine-tuning a small portion of parameters, is an effective strategy for adapting pre-trained models to downstream domains. To further reduce the memory demand, recent PETL works focus on the more valuable memory-efficient characteristic. In this paper, we argue that the scalability, adaptability, and generalizability of state-of-the-art methods are hindered by structural dependency and pertinency on specific pre-trained backbones. To this end, we propose a new memory-efficient PETL strategy, Universal Parallel Tuning (UniPT), to mitigate these weaknesses. Specifically, we facilitate the transfer process via a lightweight and learnable parallel network, which consists of: 1) A parallel interaction module that decouples the sequential connections and processes the intermediate activations detachedly from the pre-trained network. 2) A confidence aggregation module that learns optimal strategies adaptively for integrating cross-layer features. We evaluate UniPT with different backbones (e.g., T5, VSE$\infty$, CLIP4Clip, Clip-ViL, and MDETR) on various vision-and-language and pure NLP tasks. Extensive ablations on 18 datasets have validated that UniPT can not only dramatically reduce memory consumption and outperform the best competitor, but also achieve competitive performance over other plain PETL methods with lower training memory overhead. Our code is publicly available at: https://github.com/Paranioar/UniPT.

Junwen He, Yifan Wang, Lijun Wang et al. · stanford

Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation. Recent works pursue unified frameworks to tackle this challenge but mostly still treat it as two individual learning tasks, which limits their potential for exploring cross-domain information. We propose a deeply unified framework for depth-aware panoptic segmentation, which performs joint segmentation and depth estimation both in a per-segment manner with identical object queries. To narrow the gap between the two tasks, we further design a geometric query enhancement method, which is able to integrate scene geometry into object queries using latent representations. In addition, we propose a bi-directional guidance learning approach to facilitate cross-task feature learning by taking advantage of their mutual relations. Our method sets the new state of the art for depth-aware panoptic segmentation on both Cityscapes-DVPS and SemKITTI-DVPS datasets. Moreover, our guidance learning approach is shown to deliver performance improvement even under incomplete supervision labels.

Qinghe Wang, Lijie Liu, Miao Hua et al.

Image-based head swapping task aims to stitch a source head to another source body flawlessly. This seldom-studied task faces two major challenges: 1) Preserving the head and body from various sources while generating a seamless transition region. 2) No paired head swapping dataset and benchmark so far. In this paper, we propose a semantic-mixing diffusion model for head swapping (HS-Diffusion) which consists of a latent diffusion model (LDM) and a semantic layout generator. We blend the semantic layouts of source head and source body, and then inpaint the transition region by the semantic layout generator, achieving a coarse-grained head swapping. Semantic-mixing LDM can further implement a fine-grained head swapping with the inpainted layout as condition by a progressive fusion process, while preserving head and body with high-quality reconstruction. To this end, we propose a semantic calibration strategy for natural inpainting and a neck alignment for geometric realism. Importantly, we construct a new image-based head swapping benchmark and design two tailor-designed metrics (Mask-FID and Focal-FID). Extensive experiments demonstrate the superiority of our framework. The code will be available: https://github.com/qinghew/HS-Diffusion.

Jiawen Zhu, Zhenyu Chen, Zeqi Hao et al.

Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows the unification of single/multiobject and box/mask-based tracking. Among them, the Segment Anything Model (SAM) attracts much attention. In this report, we propose HQTrack, a framework for High Quality Tracking anything in videos. HQTrack mainly consists of a video multi-object segmenter (VMOS) and a mask refiner (MR). Given the object to be tracked in the initial frame of a video, VMOS propagates the object masks to the current frame. The mask results at this stage are not accurate enough since VMOS is trained on several closeset video object segmentation (VOS) datasets, which has limited ability to generalize to complex and corner scenes. To further improve the quality of tracking masks, a pretrained MR model is employed to refine the tracking results. As a compelling testament to the effectiveness of our paradigm, without employing any tricks such as test-time data augmentations and model ensemble, HQTrack ranks the 2nd place in the Visual Object Tracking and Segmentation (VOTS2023) challenge. Code and models are available at https://github.com/jiawen-zhu/HQTrack.

Youwei Pang, Xiaoqi Zhao, Lihe Zhang et al.

Deep learning (DL) has advanced the field of dense prediction, while gradually dissolving the inherent barriers between different tasks. However, most existing works focus on designing architectures and constructing visual cues only for the specific task, which ignores the potential uniformity introduced by the DL paradigm. In this paper, we attempt to construct a novel $\underline{ComP}$lementary $\underline{tr}$ansformer, $\textbf{ComPtr}$, for diverse bi-source dense prediction tasks. Specifically, unlike existing methods that over-specialize in a single task or a subset of tasks, ComPtr starts from the more general concept of bi-source dense prediction. Based on the basic dependence on information complementarity, we propose consistency enhancement and difference awareness components with which ComPtr can evacuate and collect important visual semantic cues from different image sources for diverse tasks, respectively. ComPtr treats different inputs equally and builds an efficient dense interaction model in the form of sequence-to-sequence on top of the transformer. This task-generic design provides a smooth foundation for constructing the unified model that can simultaneously deal with various bi-source information. In extensive experiments across several representative vision tasks, i.e. remote sensing change detection, RGB-T crowd counting, RGB-D/T salient object detection, and RGB-D semantic segmentation, the proposed method consistently obtains favorable performance. The code will be available at https://github.com/lartpang/ComPtr.

Tianyu Yan, Zifu Wan, Pingping Zhang et al.

In the remote sensing field, Change Detection (CD) aims to identify and localize the changed regions from dual-phase images over the same places. Recently, it has achieved great progress with the advances of deep learning. However, current methods generally deliver incomplete CD regions and irregular CD boundaries due to the limited representation ability of the extracted visual features. To relieve these issues, in this work we propose a novel Transformer-based learning framework named TransY-Net for remote sensing image CD, which improves the feature extraction from a global view and combines multi-level visual features in a pyramid manner. More specifically, the proposed framework first utilizes the advantages of Transformers in long-range dependency modeling. It can help to learn more discriminative global-level features and obtain complete CD regions. Then, we introduce a novel pyramid structure to aggregate multi-level visual features from Transformers for feature enhancement. The pyramid structure grafted with a Progressive Attention Module (PAM) can improve the feature representation ability with additional inter-dependencies through spatial and channel attentions. Finally, to better train the whole framework, we utilize the deeply-supervised learning with multiple boundary-aware loss functions. Extensive experiments demonstrate that our proposed method achieves a new state-of-the-art performance on four optical and two SAR image CD benchmarks. The source code is released at https://github.com/Drchip61/TransYNet.

Pengyu Zhang, Jie Zhao, Dong Wang et al.

With the popularity of multi-modal sensors, visible-thermal (RGB-T) object tracking is to achieve robust performance and wider application scenarios with the guidance of objects' temperature information. However, the lack of paired training samples is the main bottleneck for unlocking the power of RGB-T tracking. Since it is laborious to collect high-quality RGB-T sequences, recent benchmarks only provide test sequences. In this paper, we construct a large-scale benchmark with high diversity for visible-thermal UAV tracking (VTUAV), including 500 sequences with 1.7 million high-resolution (1920 $\times$ 1080 pixels) frame pairs. In addition, comprehensive applications (short-term tracking, long-term tracking and segmentation mask prediction) with diverse categories and scenes are considered for exhaustive evaluation. Moreover, we provide a coarse-to-fine attribute annotation, where frame-level attributes are provided to exploit the potential of challenge-specific trackers. In addition, we design a new RGB-T baseline, named Hierarchical Multi-modal Fusion Tracker (HMFT), which fuses RGB-T data in various levels. Numerous experiments on several datasets are conducted to reveal the effectiveness of HMFT and the complement of different fusion types. The project is available at here.

Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang et al.

Recent camouflaged object detection (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Apart from the high intrinsic similarity between camouflaged objects and their background, objects are usually diverse in scale, fuzzy in appearance, and even severely occluded. To this end, we propose an effective unified collaborative pyramid network that mimics human behavior when observing vague images and videos, \ie zooming in and out. Specifically, our approach employs the zooming strategy to learn discriminative mixed-scale semantics by the multi-head scale integration and rich granularity perception units, which are designed to fully explore imperceptible clues between candidate objects and background surroundings. The former's intrinsic multi-head aggregation provides more diverse visual patterns. The latter's routing mechanism can effectively propagate inter-frame differences in spatiotemporal scenarios and be adaptively deactivated and output all-zero results for static representations. They provide a solid foundation for realizing a unified architecture for static and dynamic COD. Moreover, considering the uncertainty and ambiguity derived from indistinguishable textures, we construct a simple yet effective regularization, uncertainty awareness loss, to encourage predictions with higher confidence in candidate regions. Our highly task-friendly framework consistently outperforms existing state-of-the-art methods in image and video COD benchmarks. Our code can be found at {https://github.com/lartpang/ZoomNeXt}.

Ben Kang, Xin Chen, Dong Wang et al.

Transformer-based visual trackers have demonstrated significant progress owing to their superior modeling capabilities. However, existing trackers are hampered by low speed, limiting their applicability on devices with limited computational power. To alleviate this problem, we propose HiT, a new family of efficient tracking models that can run at high speed on different devices while retaining high performance. The central idea of HiT is the Bridge Module, which bridges the gap between modern lightweight transformers and the tracking framework. The Bridge Module incorporates the high-level information of deep features into the shallow large-resolution features. In this way, it produces better features for the tracking head. We also propose a novel dual-image position encoding technique that simultaneously encodes the position information of both the search region and template images. The HiT model achieves promising speed with competitive performance. For instance, it runs at 61 frames per second (fps) on the Nvidia Jetson AGX edge device. Furthermore, HiT attains 64.6% AUC on the LaSOT benchmark, surpassing all previous efficient trackers.

Junsong Chen, Jincheng Yu, Chongjian Ge et al.

The most advanced text-to-image (T2I) models require significant training costs (e.g., millions of GPU hours), seriously hindering the fundamental innovation for the AIGC community while increasing CO2 emissions. This paper introduces PIXART-$α$, a Transformer-based T2I diffusion model whose image generation quality is competitive with state-of-the-art image generators (e.g., Imagen, SDXL, and even Midjourney), reaching near-commercial application standards. Additionally, it supports high-resolution image synthesis up to 1024px resolution with low training cost, as shown in Figure 1 and 2. To achieve this goal, three core designs are proposed: (1) Training strategy decomposition: We devise three distinct training steps that separately optimize pixel dependency, text-image alignment, and image aesthetic quality; (2) Efficient T2I Transformer: We incorporate cross-attention modules into Diffusion Transformer (DiT) to inject text conditions and streamline the computation-intensive class-condition branch; (3) High-informative data: We emphasize the significance of concept density in text-image pairs and leverage a large Vision-Language model to auto-label dense pseudo-captions to assist text-image alignment learning. As a result, PIXART-$α$'s training speed markedly surpasses existing large-scale T2I models, e.g., PIXART-$α$ only takes 10.8% of Stable Diffusion v1.5's training time (675 vs. 6,250 A100 GPU days), saving nearly \$300,000 (\$26,000 vs. \$320,000) and reducing 90% CO2 emissions. Moreover, compared with a larger SOTA model, RAPHAEL, our training cost is merely 1%. Extensive experiments demonstrate that PIXART-$α$ excels in image quality, artistry, and semantic control. We hope PIXART-$α$ will provide new insights to the AIGC community and startups to accelerate building their own high-quality yet low-cost generative models from scratch.

Xin Li, Yuqing Huang, Zhenyu He et al.

Existing visual tracking methods typically take an image patch as the reference of the target to perform tracking. However, a single image patch cannot provide a complete and precise concept of the target object as images are limited in their ability to abstract and can be ambiguous, which makes it difficult to track targets with drastic variations. In this paper, we propose the CiteTracker to enhance target modeling and inference in visual tracking by connecting images and text. Specifically, we develop a text generation module to convert the target image patch into a descriptive text containing its class and attribute information, providing a comprehensive reference point for the target. In addition, a dynamic description module is designed to adapt to target variations for more effective target representation. We then associate the target description and the search image using an attention-based correlation module to generate the correlated features for target state reference. Extensive experiments on five diverse datasets are conducted to evaluate the proposed algorithm and the favorable performance against the state-of-the-art methods demonstrates the effectiveness of the proposed tracking method.

Haiwen Diao, Jiahao Wang, Penghao Wu et al.

Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragments pixel-level signals across frames and scatters early pixel-word interactions. In parallel, native VLMs, despite impressive performance on single images, remain largely unexplored in multi-image, video understanding, and spatial intelligence. Hence, we introduce NEO-ov, a native foundation model that learns cross-frame and pixel-word correspondence end-to-end, without any external encoders, auxiliary adapters, or post-hoc fusion. By eliminating module boundaries entirely, NEO-ov enables fine-grained and unified spatiotemporal modeling to emerge natively inside the model. Notably, NEO-ov largely narrows the gap to modular counterparts while excelling at fine-grained visual perception, validating that native "one-vision" architectures are not only feasible but competitive at scale. Beyond empirical performance, we unveil systematic architectural analyses and detailed training recipes to facilitate subsequent native multimodal modeling. Our code and models are publicly available at: https://github.com/EvolvingLMMs-Lab/NEO.

Weihua He, Kaichao You, Zhendong Qiao et al.

Recording fast motion in a high FPS (frame-per-second) requires expensive high-speed cameras. As an alternative, interpolating low-FPS videos from commodity cameras has attracted significant attention. If only low-FPS videos are available, motion assumptions (linear or quadratic) are necessary to infer intermediate frames, which fail to model complex motions. Event camera, a new camera with pixels producing events of brightness change at the temporal resolution of $μs$ $(10^{-6}$ second $)$, is a game-changing device to enable video interpolation at the presence of arbitrarily complex motion. Since event camera is a novel sensor, its potential has not been fulfilled due to the lack of processing algorithms. The pioneering work Time Lens introduced event cameras to video interpolation by designing optical devices to collect a large amount of paired training data of high-speed frames and events, which is too costly to scale. To fully unlock the potential of event cameras, this paper proposes a novel TimeReplayer algorithm to interpolate videos captured by commodity cameras with events. It is trained in an unsupervised cycle-consistent style, canceling the necessity of high-speed training data and bringing the additional ability of video extrapolation. Its state-of-the-art results and demo videos in supplementary reveal the promising future of event-based vision.

Shixuan Gao, Pingping Zhang, Tianyu Yan et al.

Salient Object Detection (SOD) aims to identify and segment the most prominent objects in images. Advanced SOD methods often utilize various Convolutional Neural Networks (CNN) or Transformers for deep feature extraction. However, these methods still deliver low performance and poor generalization in complex cases. Recently, Segment Anything Model (SAM) has been proposed as a visual fundamental model, which gives strong segmentation and generalization capabilities. Nonetheless, SAM requires accurate prompts of target objects, which are unavailable in SOD. Additionally, SAM lacks the utilization of multi-scale and multi-level information, as well as the incorporation of fine-grained details. To address these shortcomings, we propose a Multi-scale and Detail-enhanced SAM (MDSAM) for SOD. Specifically, we first introduce a Lightweight Multi-Scale Adapter (LMSA), which allows SAM to learn multi-scale information with very few trainable parameters. Then, we propose a Multi-Level Fusion Module (MLFM) to comprehensively utilize the multi-level information from the SAM's encoder. Finally, we propose a Detail Enhancement Module (DEM) to incorporate SAM with fine-grained details. Experimental results demonstrate the superior performance of our model on multiple SOD datasets and its strong generalization on other segmentation tasks. The source code is released at https://github.com/BellyBeauty/MDSAM.

Takashi Isobe, Xu Jia, Xin Tao et al.

Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensation. However, such temporal modeling techniques increase the model complexity and might fail in case of occlusion or complex motion, resulting in serious distortion and artifacts. In this paper, we propose to explore the role of explicit temporal difference modeling in both LR and HR space. Instead of directly feeding consecutive frames into a VSR model, we propose to compute the temporal difference between frames and divide those pixels into two subsets according to the level of difference. They are separately processed with two branches of different receptive fields in order to better extract complementary information. To further enhance the super-resolution result, not only spatial residual features are extracted, but the difference between consecutive frames in high-frequency domain is also computed. It allows the model to exploit intermediate SR results in both future and past to refine the current SR output. The difference at different time steps could be cached such that information from further distance in time could be propagated to the current frame for refinement. Experiments on several video super-resolution benchmark datasets demonstrate the effectiveness of the proposed method and its favorable performance against state-of-the-art methods.

Xuehu Liu, Chenyang Yu, Pingping Zhang et al.

Advanced deep Convolutional Neural Networks (CNNs) have shown great success in video-based person Re-Identification (Re-ID). However, they usually focus on the most obvious regions of persons with a limited global representation ability. Recently, it witnesses that Transformers explore the inter-patch relations with global observations for performance improvements. In this work, we take both sides and propose a novel spatial-temporal complementary learning framework named Deeply-Coupled Convolution-Transformer (DCCT) for high-performance video-based person Re-ID. Firstly, we couple CNNs and Transformers to extract two kinds of visual features and experimentally verify their complementarity. Further, in spatial, we propose a Complementary Content Attention (CCA) to take advantages of the coupled structure and guide independent features for spatial complementary learning. In temporal, a Hierarchical Temporal Aggregation (HTA) is proposed to progressively capture the inter-frame dependencies and encode temporal information. Besides, a gated attention is utilized to deliver aggregated temporal information into the CNN and Transformer branches for temporal complementary learning. Finally, we introduce a self-distillation training strategy to transfer the superior spatial-temporal knowledge to backbone networks for higher accuracy and more efficiency. In this way, two kinds of typical features from same videos are integrated mechanically for more informative representations. Extensive experiments on four public Re-ID benchmarks demonstrate that our framework could attain better performances than most state-of-the-art methods.

Youwei Pang, Xiaoqi Zhao, Jiaming Zuo et al.

Recently, the emergence of the large-scale vision-language model (VLM), such as CLIP, has opened the way towards open-world object perception. Many works have explored the utilization of pre-trained VLM for the challenging open-vocabulary dense prediction task that requires perceiving diverse objects with novel classes at inference time. Existing methods construct experiments based on the public datasets of related tasks, which are not tailored for open vocabulary and rarely involve imperceptible objects camouflaged in complex scenes due to data collection bias and annotation costs. To fill in the gaps, we introduce a new task, open-vocabulary camouflaged object segmentation (OVCOS), and construct a large-scale complex scene dataset (\textbf{OVCamo}) containing 11,483 hand-selected images with fine annotations and corresponding object classes. Further, we build a strong single-stage open-vocabulary \underline{c}amouflaged \underline{o}bject \underline{s}egmentation transform\underline{er} baseline \textbf{OVCoser} attached to the parameter-fixed CLIP with iterative semantic guidance and structure enhancement. By integrating the guidance of class semantic knowledge and the supplement of visual structure cues from the edge and depth information, the proposed method can efficiently capture camouflaged objects. Moreover, this effective framework also surpasses previous state-of-the-arts of open-vocabulary semantic image segmentation by a large margin on our OVCamo dataset. With the proposed dataset and baseline, we hope that this new task with more practical value can further expand the research on open-vocabulary dense prediction tasks. Our code and data can be found in the \href{https://github.com/lartpang/OVCamo}{link}.

Jiaxing Yang, Lihe Zhang, Huchuan Lu

Lane detection is one of the core functions in autonomous driving and has aroused widespread attention recently. The networks to segment lane instances, especially with bad appearance, must be able to explore lane distribution properties. Most existing methods tend to resort to CNN-based techniques. A few have a try on incorporating the recent adorable, the seq2seq Transformer \cite{transformer}. However, their innate drawbacks of weak global information collection ability and exorbitant computation overhead prohibit a wide range of the further applications. In this work, we propose Atrous Transformer (AtrousFormer) to solve the problem. Its variant local AtrousFormer is interleaved into feature extractor to enhance extraction. Their collecting information first by rows and then by columns in a dedicated manner finally equips our network with stronger information gleaning ability and better computation efficiency. To further improve the performance, we also propose a local semantic guided decoder to delineate the identities and shapes of lanes more accurately, in which the predicted Gaussian map of the starting point of each lane serves to guide the process. Extensive results on three challenging benchmarks (CULane, TuSimple, and BDD100K) show that our network performs favorably against the state of the arts.

Jianchuan Chen, Wentao Yi, Liqian Ma et al.

In this work, we focus on synthesizing high-fidelity novel view images for arbitrary human performers, given a set of sparse multi-view images. It is a challenging task due to the large variation among articulated body poses and heavy self-occlusions. To alleviate this, we introduce an effective generalizable framework Generalizable Model-based Neural Radiance Fields (GM-NeRF) to synthesize free-viewpoint images. Specifically, we propose a geometry-guided attention mechanism to register the appearance code from multi-view 2D images to a geometry proxy which can alleviate the misalignment between inaccurate geometry prior and pixel space. On top of that, we further conduct neural rendering and partial gradient backpropagation for efficient perceptual supervision and improvement of the perceptual quality of synthesis. To evaluate our method, we conduct experiments on synthesized datasets THuman2.0 and Multi-garment, and real-world datasets Genebody and ZJUMocap. The results demonstrate that our approach outperforms state-of-the-art methods in terms of novel view synthesis and geometric reconstruction.

Xiaoqi Zhao, Youwei Pang, Lihe Zhang et al.

In many binary segmentation tasks, most CNNs-based methods use a U-shape encoder-decoder network as their basic structure. They ignore two key problems when the encoder exchanges information with the decoder: one is the lack of interference control mechanism between them, the other is without considering the disparity of the contributions from different encoder levels. In this work, we propose a simple yet general gated network (GateNet) to tackle them all at once. With the help of multi-level gate units, the valuable context information from the encoder can be selectively transmitted to the decoder. In addition, we design a gated dual branch structure to build the cooperation among the features of different levels and improve the discrimination ability of the network. Furthermore, we introduce a "Fold" operation to improve the atrous convolution and form a novel folded atrous convolution, which can be flexibly embedded in ASPP or DenseASPP to accurately localize foreground objects of various scales. GateNet can be easily generalized to many binary segmentation tasks, including general and specific object segmentation and multi-modal segmentation. Without bells and whistles, our network consistently performs favorably against the state-of-the-art methods under 10 metrics on 33 datasets of 10 binary segmentation tasks.

Dongsheng Wang, Xu Jia, Yang Zhang et al.

Event-based cameras are bio-inspired sensors that capture brightness change of every pixel in an asynchronous manner. Compared with frame-based sensors, event cameras have microsecond-level latency and high dynamic range, hence showing great potential for object detection under high-speed motion and poor illumination conditions. Due to sparsity and asynchronism nature with event streams, most of existing approaches resort to hand-crafted methods to convert event data into 2D grid representation. However, they are sub-optimal in aggregating information from event stream for object detection. In this work, we propose to learn an event representation optimized for event-based object detection. Specifically, event streams are divided into grids in the x-y-t coordinates for both positive and negative polarity, producing a set of pillars as 3D tensor representation. To fully exploit information with event streams to detect objects, a dual-memory aggregation network (DMANet) is proposed to leverage both long and short memory along event streams to aggregate effective information for object detection. Long memory is encoded in the hidden state of adaptive convLSTMs while short memory is modeled by computing spatial-temporal correlation between event pillars at neighboring time intervals. Extensive experiments on the recently released event-based automotive detection dataset demonstrate the effectiveness of the proposed method.

Xuehu Liu, Pingping Zhang, Huchuan Lu

Video-based person Re-Identification (V-ReID) aims to retrieve specific persons from raw videos captured by non-overlapped cameras. As a fundamental task, it spreads many multimedia and computer vision applications. However, due to the variations of persons and scenes, there are still many obstacles that must be overcome for high performance. In this work, we notice that both the long-term and short-term information of persons are important for robust video representations. Thus, we propose a novel deep learning framework named Long Short-Term Representation Learning (LSTRL) for effective V-ReID. More specifically, to extract long-term representations, we propose a Multi-granularity Appearance Extractor (MAE), in which four granularity appearances are effectively captured across multiple frames. Meanwhile, to extract short-term representations, we propose a Bi-direction Motion Estimator (BME), in which reciprocal motion information is efficiently extracted from consecutive frames. The MAE and BME are plug-and-play and can be easily inserted into existing networks for efficient feature learning. As a result, they significantly improve the feature representation ability for V-ReID. Extensive experiments on three widely used benchmarks show that our proposed approach can deliver better performances than most state-of-the-arts.

Chongjian Ge, Junsong Chen, Enze Xie et al.

Perception systems in modern autonomous driving vehicles typically take inputs from complementary multi-modal sensors, e.g., LiDAR and cameras. However, in real-world applications, sensor corruptions and failures lead to inferior performances, thus compromising autonomous safety. In this paper, we propose a robust framework, called MetaBEV, to address extreme real-world environments involving overall six sensor corruptions and two extreme sensor-missing situations. In MetaBEV, signals from multiple sensors are first processed by modal-specific encoders. Subsequently, a set of dense BEV queries are initialized, termed meta-BEV. These queries are then processed iteratively by a BEV-Evolving decoder, which selectively aggregates deep features from either LiDAR, cameras, or both modalities. The updated BEV representations are further leveraged for multiple 3D prediction tasks. Additionally, we introduce a new M2oE structure to alleviate the performance drop on distinct tasks in multi-task joint learning. Finally, MetaBEV is evaluated on the nuScenes dataset with 3D object detection and BEV map segmentation tasks. Experiments show MetaBEV outperforms prior arts by a large margin on both full and corrupted modalities. For instance, when the LiDAR signal is missing, MetaBEV improves 35.5% detection NDS and 17.7% segmentation mIoU upon the vanilla BEVFusion model; and when the camera signal is absent, MetaBEV still achieves 69.2% NDS and 53.7% mIoU, which is even higher than previous works that perform on full-modalities. Moreover, MetaBEV performs fairly against previous methods in both canonical perception and multi-task learning settings, refreshing state-of-the-art nuScenes BEV map segmentation with 70.4% mIoU.

Haojie Zhao, Junsong Chen, Lijun Wang et al.

Compared with traditional RGB-only visual tracking, few datasets have been constructed for RGB-D tracking. In this paper, we propose ARKitTrack, a new RGB-D tracking dataset for both static and dynamic scenes captured by consumer-grade LiDAR scanners equipped on Apple's iPhone and iPad. ARKitTrack contains 300 RGB-D sequences, 455 targets, and 229.7K video frames in total. Along with the bounding box annotations and frame-level attributes, we also annotate this dataset with 123.9K pixel-level target masks. Besides, the camera intrinsic and camera pose of each frame are provided for future developments. To demonstrate the potential usefulness of this dataset, we further present a unified baseline for both box-level and pixel-level tracking, which integrates RGB features with bird's-eye-view representations to better explore cross-modality 3D geometry. In-depth empirical analysis has verified that the ARKitTrack dataset can significantly facilitate RGB-D tracking and that the proposed baseline method compares favorably against the state of the arts. The code and dataset is available at https://arkittrack.github.io.

Fan Zhao, Wenda Zhao, Huchuan Lu

General deep learning-based methods for infrared and visible image fusion rely on the unsupervised mechanism for vital information retention by utilizing elaborately designed loss functions. However, the unsupervised mechanism depends on a well designed loss function, which cannot guarantee that all vital information of source images is sufficiently extracted. In this work, we propose a novel interactive feature embedding in self-supervised learning framework for infrared and visible image fusion, attempting to overcome the issue of vital information degradation. With the help of self-supervised learning framework, hierarchical representations of source images can be efficiently extracted. In particular, interactive feature embedding models are tactfully designed to build a bridge between the self-supervised learning and infrared and visible image fusion learning, achieving vital information retention. Qualitative and quantitative evaluations exhibit that the proposed method performs favorably against state-of-the-art methods.

Xiaoqi Zhao, Shijie Chang, Youwei Pang et al.

Static and moving objects often occur in real-life videos. Most video object segmentation methods only focus on extracting and exploiting motion cues to perceive moving objects. Once faced with the frames of static objects, the moving object predictors may predict failed results caused by uncertain motion information, such as low-quality optical flow maps. Besides, different sources such as RGB, depth, optical flow and static saliency can provide useful information about the objects. However, existing approaches only consider either the RGB or RGB and optical flow. In this paper, we propose a novel adaptive multi-source predictor for zero-shot video object segmentation (ZVOS). In the static object predictor, the RGB source is converted to depth and static saliency sources, simultaneously. In the moving object predictor, we propose the multi-source fusion structure. First, the spatial importance of each source is highlighted with the help of the interoceptive spatial attention module (ISAM). Second, the motion-enhanced module (MEM) is designed to generate pure foreground motion attention for improving the representation of static and moving features in the decoder. Furthermore, we design a feature purification module (FPM) to filter the inter-source incompatible features. By using the ISAM, MEM and FPM, the multi-source features are effectively fused. In addition, we put forward an adaptive predictor fusion network (APF) to evaluate the quality of the optical flow map and fuse the predictions from the static object predictor and the moving object predictor in order to prevent over-reliance on the failed results caused by low-quality optical flow maps. Experiments show that the proposed model outperforms the state-of-the-art methods on three challenging ZVOS benchmarks. And, the static object predictor precisely predicts a high-quality depth map and static saliency map at the same time.

Shijie Chang, Lihe Zhang, Huchuan Lu

Existing few-shot segmentation (FSS) methods mainly focus on designing novel support-query matching and self-matching mechanisms to exploit implicit knowledge in pre-trained backbones. However, the performance of these methods is often constrained by models pre-trained on classification tasks. The exploration of what types of pre-trained models can provide more beneficial implicit knowledge for FSS remains limited. In this paper, inspired by the representation consistency of foundational computer vision models, we develop a FSS framework based on foundation models. To be specific, we propose a simple approach to extract implicit knowledge from foundation models to construct coarse correspondence and introduce a lightweight decoder to refine coarse correspondence for fine-grained segmentation. We systematically summarize the performance of various foundation models on FSS and discover that the implicit knowledge within some of these models is more beneficial for FSS than models pre-trained on classification tasks. Extensive experiments on two widely used datasets demonstrate the effectiveness of our approach in leveraging the implicit knowledge of foundation models. Notably, the combination of DINOv2 and DFN exceeds previous state-of-the-art methods by 17.5% on COCO-20i. Code is available at https://github.com/DUT-CSJ/FoundationFSS.

Haiwen Diao, Bo Wan, Xu Jia et al.

Parameter-efficient transfer learning (PETL) has emerged as a flourishing research field for adapting large pre-trained models to downstream tasks, greatly reducing trainable parameters while grappling with memory challenges during fine-tuning. To address it, memory-efficient series (METL) avoid backpropagating gradients through the large backbone. However, they compromise by exclusively relying on frozen intermediate outputs and limiting the exhaustive exploration of prior knowledge from pre-trained models. Moreover, the dependency and redundancy between cross-layer features are frequently overlooked, thereby submerging more discriminative representations and causing an inherent performance gap (vs. conventional PETL methods). Hence, we propose an innovative METL strategy called SHERL for resource-limited scenarios to decouple the entire adaptation into two successive and complementary processes. In the early route, intermediate outputs are consolidated via an anti-redundancy operation, enhancing their compatibility for subsequent interactions; thereby in the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead and regulate these fairly flexible features into more adaptive and powerful representations for new domains. Extensive ablations on vision-and-language and language-only tasks show that SHERL combines the strengths of both parameter and memory-efficient techniques, performing on-par or better across diverse architectures with lower memory during fine-tuning. Our code is publicly available at: https://github.com/Paranioar/SHERL.

Jiawen Zhu, Xin Chen, Pengyu Zhang et al.

The dominant trackers generate a fixed-size rectangular region based on the previous prediction or initial bounding box as the model input, i.e., search region. While this manner obtains promising tracking efficiency, a fixed-size search region lacks flexibility and is likely to fail in some cases, e.g., fast motion and distractor interference. Trackers tend to lose the target object due to the limited search region or experience interference from distractors due to the excessive search region. Drawing inspiration from the pattern humans track an object, we propose a novel tracking paradigm, called Search Region Regulation Tracking (SRRT) that applies a small eyereach when the target is captured and zooms out the search field when the target is about to be lost. SRRT applies a proposed search region regulator to estimate an optimal search region dynamically for each frame, by which the tracker can flexibly respond to transient changes in the location of object occurrences. To adapt the object's appearance variation during online tracking, we further propose a lockingstate determined updating strategy for reference frame updating. The proposed SRRT is concise without bells and whistles, yet achieves evident improvements and competitive results with other state-of-the-art trackers on eight benchmarks. On the large-scale LaSOT benchmark, SRRT improves SiamRPN++ and TransT with absolute gains of 4.6% and 3.1% in terms of AUC. The code and models will be released.

Jiannan Wu, Yi Jiang, Bin Yan et al.

Open-world instance segmentation is a rising task, which aims to segment all objects in the image by learning from a limited number of base-category objects. This task is challenging, as the number of unseen categories could be hundreds of times larger than that of seen categories. Recently, the DETR-like models have been extensively studied in the closed world while stay unexplored in the open world. In this paper, we utilize the Transformer for open-world instance segmentation and present SWORD. Firstly, we introduce to attach the stop-gradient operation before classification head and further add IoU heads for discovering novel objects. We demonstrate that a simple stop-gradient operation not only prevents the novel objects from being suppressed as background, but also allows the network to enjoy the merit of heuristic label assignment. Secondly, we propose a novel contrastive learning framework to enlarge the representations between objects and background. Specifically, we maintain a universal object queue to obtain the object center, and dynamically select positive and negative samples from the object queries for contrastive learning. While the previous works only focus on pursuing average recall and neglect average precision, we show the prominence of SWORD by giving consideration to both criteria. Our models achieve state-of-the-art performance in various open-world cross-category and cross-dataset generalizations. Particularly, in VOC to non-VOC setup, our method sets new state-of-the-art results of 40.0% on ARb100 and 34.9% on ARm100. For COCO to UVO generalization, SWORD significantly outperforms the previous best open-world model by 5.9% on APm and 8.1% on ARm100.

Jianchuan Chen, Wentao Yi, Tiantian Wang et al.

In this report, we focus on reconstructing clothed humans in the canonical space given multiple views and poses of a human as the input. To achieve this, we utilize the geometric prior of the SMPLX model in the canonical space to learn the implicit representation for geometry reconstruction. Based on the observation that the topology between the posed mesh and the mesh in the canonical space are consistent, we propose to learn latent codes on the posed mesh by leveraging multiple input images and then assign the latent codes to the mesh in the canonical space. Specifically, we first leverage normal and geometry networks to extract the feature vector for each vertex on the SMPLX mesh. Normal maps are adopted for better generalization to unseen images compared to 2D images. Then, features for each vertex on the posed mesh from multiple images are integrated by MLPs. The integrated features acting as the latent code are anchored to the SMPLX mesh in the canonical space. Finally, latent code for each 3D point is extracted and utilized to calculate the SDF. Our work for reconstructing the human shape on canonical pose achieves 3rd performance on WCPA MVP-Human Body Challenge.

Jie Zhao, Johan Edstedt, Michael Felsberg et al.

Due to long-distance correlation and powerful pretrained models, transformer-based methods have initiated a breakthrough in visual object tracking performance. Previous works focus on designing effective architectures suited for tracking, but ignore that data augmentation is equally crucial for training a well-performing model. In this paper, we first explore the impact of general data augmentations on transformer-based trackers via systematic experiments, and reveal the limited effectiveness of these common strategies. Motivated by experimental observations, we then propose two data augmentation methods customized for tracking. First, we optimize existing random cropping via a dynamic search radius mechanism and simulation for boundary samples. Second, we propose a token-level feature mixing augmentation strategy, which enables the model against challenges like background interference. Extensive experiments on two transformer-based trackers and six benchmarks demonstrate the effectiveness and data efficiency of our methods, especially under challenging settings, like one-shot tracking and small image resolutions.

Jingjing Li, Yue Feng, Yuchen Guo et al.

Segment Anything Model 3 (SAM3) has advanced open-vocabulary segmentation through promptable concept segmentation, allowing users to segment all instances corresponding to a given concept, typically specified with short noun-phrase (NP) prompts. While this marks the first integration of language-level concepts within the SAM family, real-world usage typically requires far richer expressions that include attributes, spatial relations, functionalities, actions, states, and even implicit reasoning over instances. Currently, SAM3 relies on external multi-modal agents to convert complex instructions into NPs and then conduct iterative mask filtering. However, these NP-level concepts remain overly coarse, often failing to precisely represent a specific instance. In this work, we present SAM3-I, an enhanced framework that unifies concept-level understanding and instruction-level reasoning within the SAM family. SAM3-I introduces an instruction-aware cascaded adaptation mechanism that progressively aligns expressive instruction semantics with SAM3's existing vision-language representations, enabling direct instruction-following segmentation without sacrificing its original concept-driven capabilities. Furthermore, we design a structured instruction taxonomy spanning concept, simple, and complex levels, and develop a scalable data engine to construct a dataset with diverse instruction-mask pairs. Experiments show that SAM3-I delivers appealing performance, demonstrating that SAM3 can be effectively extended to follow natural-language instructions while preserving its strong concept grounding. We open-source SAM3-I and provide practical fine-tuning workflows, enabling researchers to adapt it to domain-specific applications. The source code is available here.

Xin Li, Deshui Miao, Zhenyu He et al.

Tracking and segmenting multiple similar objects with distinct or complex parts in long-term videos is particularly challenging due to the ambiguity in identifying target components and the confusion caused by occlusion, background clutter, and changes in appearance or environment over time. In this paper, we propose a robust video object segmentation framework that learns spatial-semantic features and discriminative object queries to address the above issues. Specifically, we construct a spatial-semantic block comprising a semantic embedding component and a spatial dependency modeling part for associating global semantic features and local spatial features, providing a comprehensive target representation. In addition, we develop a masked cross-attention module to generate object queries that focus on the most discriminative parts of target objects during query propagation, alleviating noise accumulation to ensure effective long-term query propagation. Extensive experimental results show that the proposed method achieves state-of-the-art performance on benchmark data sets, including the DAVIS2017 test (\textbf{87.8\%}), YoutubeVOS 2019 (\textbf{88.1\%}), MOSE val (\textbf{74.0\%}), and LVOS test (\textbf{73.0\%}), and demonstrate the effectiveness and generalization capacity of our model. The source code and trained models are released at \href{https://github.com/yahooo-m/S3}{https://github.com/yahooo-m/S3}.

Youwei Pang, Changsheng Gao, Dong Liu et al.

Large models have delivered remarkable performance across a wide range of perception and generation tasks, yet practical deployment is increasingly constrained by computational and memory budgets, as well as privacy requirements. Split execution alleviates these constraints by partitioning computation across devices, but it inevitably introduces intensive transmission and storage of intermediate features. Unlike conventional feature coding for CNNs that typically targets homogeneous spatial activation maps, modern large models generate heterogeneous features with varying statistical distributions and compression tolerances, e.g., multi-level/multi-modal representations and autoregressive context caches. These characteristics necessitate treating large model feature coding (LaMoFC) as a fundamental system component and call for a systematic evaluation framework. In this paper, we present a comprehensive benchmark and evaluation framework for LaMoFC. We first build the feature dataset LaMoFCBench, covering diverse task requirements across 4 categories and 16 scenarios while integrating widelyadopted architectures and various split-computing settings. We then specify representative split points according to practical application scenarios to extract intermediate features, establishing a unified pipeline for fair and reproducible comparisons. Finally, we benchmark mainstream universal feature codecs, exposing the profound misalignment between existing coding paradigms and the heterogeneous nature of large model features. These findings reveal that LaMoFC demands a fundamental departure from existing paradigms, and LaMoFCBench provides the shared empirical foundation to drive this transition. The data and code will be available at https://github.com/lartpang/LaMoFCBench.

Kai Peng, Yunzhe Shen, Miao Zhang et al.

The ability to capture and segment sounding objects in dynamic visual scenes is crucial for the development of Audio-Visual Segmentation (AVS) tasks. While significant progress has been made in this area, the interaction between audio and visual modalities still requires further exploration. In this work, we aim to answer the following questions: How can a model effectively suppress audio noise while enhancing relevant audio information? How can we achieve discriminative interaction between the audio and visual modalities? To this end, we propose SDAVS, equipped with the Selective Noise-Resilient Processor (SNRP) module and the Discriminative Audio-Visual Mutual Fusion (DAMF) strategy. The proposed SNRP mitigates audio noise interference by selectively emphasizing relevant auditory cues, while DAMF ensures more consistent audio-visual representations. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on benchmark AVS datasets, especially in multi-source and complex scenes. \textit{The code and model are available at https://github.com/happylife-pk/SDAVS}.