Lv Tang

Lv Tang, Haoke Xiao, Bo Li

SAM is a segmentation model recently released by Meta AI Research and has been gaining attention quickly due to its impressive performance in generic object segmentation. However, its ability to generalize to specific scenes such as camouflaged scenes is still unknown. Camouflaged object detection (COD) involves identifying objects that are seamlessly integrated into their surroundings and has numerous practical applications in fields such as medicine, art, and agriculture. In this study, we try to ask if SAM can address the COD task and evaluate the performance of SAM on the COD benchmark by employing maximum segmentation evaluation and camouflage location evaluation. We also compare SAM's performance with 22 state-of-the-art COD methods. Our results indicate that while SAM shows promise in generic object segmentation, its performance on the COD task is limited. This presents an opportunity for further research to explore how to build a stronger SAM that may address the COD task. The results of this paper are provided in \url{https://github.com/luckybird1994/SAMCOD}.

Lv Tang, Peng-Tao Jiang, Zhihao Shen et al.

In this paper, we introduce a novel multimodal camo-perceptive framework (MMCPF) aimed at handling zero-shot Camouflaged Object Detection (COD) by leveraging the powerful capabilities of Multimodal Large Language Models (MLLMs). Recognizing the inherent limitations of current COD methodologies, which predominantly rely on supervised learning models demanding extensive and accurately annotated datasets, resulting in weak generalization, our research proposes a zero-shot MMCPF that circumvents these challenges. Although MLLMs hold significant potential for broad applications, their effectiveness in COD is hindered and they would make misinterpretations of camouflaged objects. To address this challenge, we further propose a strategic enhancement called the Chain of Visual Perception (CoVP), which significantly improves the perceptual capabilities of MLLMs in camouflaged scenes by leveraging both linguistic and visual cues more effectively. We validate the effectiveness of MMCPF on five widely used COD datasets, containing CAMO, COD10K, NC4K, MoCA-Mask and OVCamo. Experiments show that MMCPF can outperform all existing state-of-the-art zero-shot COD methods, and achieve competitive performance compared to weakly-supervised and fully-supervised methods, which demonstrates the potential of MMCPF. The Github link of this paper is \url{https://github.com/luckybird1994/MMCPF}.

Lv Tang, Bo Li

The Segment Anything Model (SAM), introduced by Meta AI Research as a generic object segmentation model, quickly garnered widespread attention and significantly influenced the academic community. To extend its application to video, Meta further develops Segment Anything Model 2 (SAM2), a unified model capable of both video and image segmentation. SAM2 shows notable improvements over its predecessor in terms of applicable domains, promptable segmentation accuracy, and running speed. However, this report reveals a decline in SAM2's ability to perceive different objects in images without prompts in its auto mode, compared to SAM. Specifically, we employ the challenging task of camouflaged object detection to assess this performance decrease, hoping to inspire further exploration of the SAM model family by researchers. The results of this paper are provided in \url{https://github.com/luckybird1994/SAMCOD}.

Bo Li, Lv Tang, Senyun Kuang et al.

In this paper, we present a novel model for simultaneous stable co-saliency detection (CoSOD) and object co-segmentation (CoSEG). To detect co-saliency (segmentation) accurately, the core problem is to well model inter-image relations between an image group. Some methods design sophisticated modules, such as recurrent neural network (RNN), to address this problem. However, order-sensitive problem is the major drawback of RNN, which heavily affects the stability of proposed CoSOD (CoSEG) model. In this paper, inspired by RNN-based model, we first propose a multi-path stable recurrent unit (MSRU), containing dummy orders mechanisms (DOM) and recurrent unit (RU). Our proposed MSRU not only helps CoSOD (CoSEG) model captures robust inter-image relations, but also reduces order-sensitivity, resulting in a more stable inference and training process. { Moreover, we design a cross-order contrastive loss (COCL) that can further address order-sensitive problem by pulling close the feature embedding generated from different input orders.} We validate our model on five widely used CoSOD datasets (CoCA, CoSOD3k, Cosal2015, iCoseg and MSRC), and three widely used datasets (Internet, iCoseg and PASCAL-VOC) for object co-segmentation, the performance demonstrates the superiority of the proposed approach as compared to the state-of-the-art (SOTA) methods.

Lv Tang, Peng-Tao Jiang, Hao-Ke Xiao et al.

The realm of computer vision has witnessed a paradigm shift with the advent of foundational models, mirroring the transformative influence of large language models in the domain of natural language processing. This paper delves into the exploration of open-world segmentation, presenting a novel approach called Image Prompt Segmentation (IPSeg) that harnesses the power of vision foundational models. IPSeg lies the principle of a training-free paradigm, which capitalizes on image prompt techniques. Specifically, IPSeg utilizes a single image containing a subjective visual concept as a flexible prompt to query vision foundation models like DINOv2 and Stable Diffusion. Our approach extracts robust features for the prompt image and input image, then matches the input representations to the prompt representations via a novel feature interaction module to generate point prompts highlighting target objects in the input image. The generated point prompts are further utilized to guide the Segment Anything Model to segment the target object in the input image. The proposed method stands out by eliminating the need for exhaustive training sessions, thereby offering a more efficient and scalable solution. Experiments on COCO, PASCAL VOC, and other datasets demonstrate IPSeg's efficacy for flexible open-world segmentation using intuitive image prompts. This work pioneers tapping foundation models for open-world understanding through visual concepts conveyed in images.

Haoke Xiao, Lv Tang, Bo Li et al.

Co-salient Object Detection (CoSOD) endeavors to replicate the human visual system's capacity to recognize common and salient objects within a collection of images. Despite recent advancements in deep learning models, these models still rely on training with well-annotated CoSOD datasets. The exploration of training-free zero-shot CoSOD frameworks has been limited. In this paper, taking inspiration from the zero-shot transfer capabilities of foundational computer vision models, we introduce the first zero-shot CoSOD framework that harnesses these models without any training process. To achieve this, we introduce two novel components in our proposed framework: the group prompt generation (GPG) module and the co-saliency map generation (CMP) module. We evaluate the framework's performance on widely-used datasets and observe impressive results. Our approach surpasses existing unsupervised methods and even outperforms fully supervised methods developed before 2020, while remaining competitive with some fully supervised methods developed before 2022.

Lv Tang, Xinfeng Zhang, Gai Zhang et al.

Video compression has always been a popular research area, where many traditional and deep video compression methods have been proposed. These methods typically rely on signal prediction theory to enhance compression performance by designing high efficient intra and inter prediction strategies and compressing video frames one by one. In this paper, we propose a novel model-based video compression (MVC) framework that regards scenes as the fundamental units for video sequences. Our proposed MVC directly models the intensity variation of the entire video sequence in one scene, seeking non-redundant representations instead of reducing redundancy through spatio-temporal predictions. To achieve this, we employ implicit neural representation as our basic modeling architecture. To improve the efficiency of video modeling, we first propose context-related spatial positional embedding and frequency domain supervision in spatial context enhancement. For temporal correlation capturing, we design the scene flow constrain mechanism and temporal contrastive loss. Extensive experimental results demonstrate that our method achieves up to a 20\% bitrate reduction compared to the latest video coding standard H.266 and is more efficient in decoding than existing video coding strategies.

Lv Tang, Tianyi Zheng, Bo Li et al.

Unified multimodal large language models (MLLMs) integrate image understanding and generation in a single framework, with the visual tokenizer acting as the sole interface that maps visual inputs into tokens for downstream tasks. However, existing shared-token designs are mostly architecture-driven and lack an explicit criterion for what information tokens should preserve to support both understanding and generation. Therefore, we introduce a capacity-constrained perspective, highlighting that in shared-token unified MLLMs the visual tokenizer behaves as a compute-bounded learner, so the token budget should prioritize reusable structure over hard-to-exploit high-entropy variations and redundancy. Motivated by this perspective, we propose InfoTok, an information-regularized visual tokenization mechanism grounded in the Information Bottleneck (IB) principle. InfoTok formulates tokenization as controlling information flow from images to shared tokens to multimodal outputs, yielding a principled trade-off between compression and task relevance via mutual-information regularization. We integrate InfoTok into three representative unified MLLMs without introducing any additional training data. Experiments show consistent improvements on both understanding and generation, supporting information-regularized tokenization as a principled foundation for learning a shared token space in unified MLLMs.

Lv Tang, Tianyi Zheng, Yang Liu et al.

Visual text compression (VTC) promises efficient long-context processing by rendering text into an image and re-encoding it with a vision-language model, often producing $3$--$20\times$ fewer decoder tokens than subword tokenization. Yet token savings do not translate predictably into downstream utility: on some tasks the visual path matches or exceeds the text path, on others it collapses, and the compression ratio itself does not predict which regime will occur. The missing quantity is therefore not another summary of efficiency, but a principled measure of task-relevant information loss induced by visual encoding. We address this problem by formulating VTC in the language of measure transport. Treating text and visual tokens as empirical probability measures, we show that the ViT patch encoder induces a push-forward map whose transport cost decomposes into a precision cost from within-patch aggregation and a coverage cost from cross-patch fragmentation. Both terms are estimable from downstream-label-free probes. This formulation yields two operational consequences: a downstream-label-free routing criterion that selects whether to use the visual path for a given input or benchmark instance, and a transport-informed foveation mechanism that re-encodes high-cost regions at higher resolution. Across $24$ NLP datasets at Qwen3-4B, our label-free rule matches the per-dataset oracle on $17/24$ datasets ($70.8\%$), and improves the average task score by $+3.3\%$ with $-10.3\%$ average tokens relative to a pure-LLM.

Bo Li, Haoke Xiao, Lv Tang

In the evolving landscape of computer vision, foundation models have emerged as pivotal tools, exhibiting exceptional adaptability to a myriad of tasks. Among these, the Segment Anything Model (SAM) by Meta AI has distinguished itself in image segmentation. However, SAM, like its counterparts, encounters limitations in specific niche applications, prompting a quest for enhancement strategies that do not compromise its inherent capabilities. This paper introduces ASAM, a novel methodology that amplifies SAM's performance through adversarial tuning. We harness the potential of natural adversarial examples, inspired by their successful implementation in natural language processing. By utilizing a stable diffusion model, we augment a subset (1%) of the SA-1B dataset, generating adversarial instances that are more representative of natural variations rather than conventional imperceptible perturbations. Our approach maintains the photorealism of adversarial examples and ensures alignment with original mask annotations, thereby preserving the integrity of the segmentation task. The fine-tuned ASAM demonstrates significant improvements across a diverse range of segmentation tasks without necessitating additional data or architectural modifications. The results of our extensive evaluations confirm that ASAM establishes new benchmarks in segmentation tasks, thereby contributing to the advancement of foundational models in computer vision. Our project page is in https://asam2024.github.io/.

Lv Tang, HaoKe Xiao, Peng-Tao Jiang et al.

Foundational models have significantly advanced in natural language processing (NLP) and computer vision (CV), with the Transformer architecture becoming a standard backbone. However, the Transformer's quadratic complexity poses challenges for handling longer sequences and higher resolution images. To address this challenge, State Space Models (SSMs) like Mamba have emerged as efficient alternatives, initially matching Transformer performance in NLP tasks and later surpassing Vision Transformers (ViTs) in various CV tasks. To improve the performance of SSMs, one crucial aspect is effective serialization of image patches. Existing methods, relying on linear scanning curves, often fail to capture complex spatial relationships and produce repetitive patterns, leading to biases. To address these limitations, we propose using fractal scanning curves for patch serialization. Fractal curves maintain high spatial proximity and adapt to different image resolutions, avoiding redundancy and enhancing SSMs' ability to model complex patterns accurately. We validate our method in image classification, detection, and segmentation tasks, and the superior performance validates its effectiveness.

Jia Wang, Xinfeng Zhang, Gai Zhang et al.

Implicit Neural Representations (INRs) have demonstrated significant potential in video compression by representing videos as neural networks. However, as the number of frames increases, the memory consumption for training and inference increases substantially, posing challenges in resource-constrained scenarios. Inspired by the success of traditional video compression frameworks, which process video frame by frame and can efficiently compress long videos, we adopt this modeling strategy for INRs to decrease memory consumption, while aiming to unify the frameworks from the perspective of timeline-based autoregressive modeling. In this work, we present a novel understanding of INR models from an autoregressive (AR) perspective and introduce a Unified AutoRegressive Framework for memory-efficient Neural Video Compression (UAR-NVC). UAR-NVC integrates timeline-based and INR-based neural video compression under a unified autoregressive paradigm. It partitions videos into several clips and processes each clip using a different INR model instance, leveraging the advantages of both compression frameworks while allowing seamless adaptation to either in form. To further reduce temporal redundancy between clips, we design two modules to optimize the initialization, training, and compression of these model parameters. UAR-NVC supports adjustable latencies by varying the clip length. Extensive experimental results demonstrate that UAR-NVC, with its flexible video clip setting, can adapt to resource-constrained environments and significantly improve performance compared to different baseline models. The project page: "https://wj-inf.github.io/UAR-NVC-page/".

Lv Tang, Jun Zhu, Xinfeng Zhang et al.

Recent advances in video compression introduce implicit neural representation (INR) based methods, which effectively capture global dependencies and characteristics of entire video sequences. Unlike traditional and deep learning based approaches, INR-based methods optimize network parameters from a global perspective, resulting in superior compression potential. However, most current INR methods utilize a fixed and uniform network architecture across all frames, limiting their adaptability to dynamic variations within and between video sequences. This often leads to suboptimal compression outcomes as these methods struggle to capture the distinct nuances and transitions in video content. To overcome these challenges, we propose Content Adaptive Neural Representation for Video Compression (CANeRV), an innovative INR-based video compression network that adaptively conducts structure optimisation based on the specific content of each video sequence. To better capture dynamic information across video sequences, we propose a dynamic sequence-level adjustment (DSA). Furthermore, to enhance the capture of dynamics between frames within a sequence, we implement a dynamic frame-level adjustment (DFA). {Finally, to effectively capture spatial structural information within video frames, thereby enhancing the detail restoration capabilities of CANeRV, we devise a structure level hierarchical structural adaptation (HSA).} Experimental results demonstrate that CANeRV can outperform both H.266/VVC and state-of-the-art INR-based video compression techniques across diverse video datasets.

Jun Zhu, Xinfeng Zhang, Lv Tang et al.

Video compression has recently benefited from implicit neural representations (INRs), which model videos as continuous functions. INRs offer compact storage and flexible reconstruction, providing a promising alternative to traditional codecs. However, most existing INR-based methods treat the temporal dimension as an independent input, limiting their ability to capture complex temporal dependencies. To address this, we propose a Hierarchical Temporal Neural Representation for Videos, TeNeRV. TeNeRV integrates short- and long-term dependencies through two key components. First, an Inter-Frame Feature Fusion (IFF) module aggregates features from adjacent frames, enforcing local temporal coherence and capturing fine-grained motion. Second, a GoP-Adaptive Modulation (GAM) mechanism partitions videos into Groups-of-Pictures and learns group-specific priors. The mechanism modulates network parameters, enabling adaptive representations across different GoPs. Extensive experiments demonstrate that TeNeRV consistently outperforms existing INR-based methods in rate-distortion performance, validating the effectiveness of our proposed approach.

Jun Zhu, Xinfeng Zhang, Lv Tang et al.

Implicit Neural Representations (INRs) have emerged as a promising paradigm for video compression. However, existing INR-based frameworks typically suffer from inherent spectral bias, which favors low-frequency components and leads to over-smoothed reconstructions and suboptimal rate-distortion performance. In this paper, we propose FaNeRV, a Frequency-aware Neural Representation for videos, which explicitly decouples low- and high-frequency components to enable efficient and faithful video reconstruction. FaNeRV introduces a multi-resolution supervision strategy that guides the network to progressively capture global structures and fine-grained textures through staged supervision . To further enhance high-frequency reconstruction, we propose a dynamic high-frequency injection mechanism that adaptively emphasizes challenging regions. In addition, we design a frequency-decomposed network module to improve feature modeling across different spectral bands. Extensive experiments on standard benchmarks demonstrate that FaNeRV significantly outperforms state-of-the-art INR methods and achieves competitive rate-distortion performance against traditional codecs.

Changxin Huang, Lv Tang, Zhaohuan Zhan et al.

Vision-and-Language Navigation (VLN) requires agents to autonomously navigate complex environments via visual images and natural language instructions--remains highly challenging. Recent research on enhancing language-guided navigation reasoning using pre-trained large language models (LLMs) has shown promising prospects. However, the reasoning of such methods is limited to the linguistic modality, lacking visual reasoning capabilities. Moreover, existing reasoning modules are optimized separately from navigation policies, leading to incompatibility and potential conflicts in optimization objectives.To tackle these challenges, we introduce UNeMo, a novel framework designed for the collaborative optimization of visual state reasoning and navigational decision-making. It introduces a Multimodal World Model (MWM) that takes visual features, language instructions, and navigational actions as inputs to jointly predict subsequent visual states, enabling cross-modal reasoning. Via a Hierarchical Prediction-Feedback (HPN) mechanism, MWM collaborates with navigation policies: the first layer generates actions using current vision-and-language features; MWM then infers post-action visual states to guide the second layer's fine-grained decisions. This forms a dynamic bidirectional promotion mechanism where MWM reasoning optimizes navigation policies, while policy decisions feedback to improve MWM's reasoning accuracy. Experiments on R2R and REVERIE datasets show UNeMo outperforms state-of-the-art methods by 2.1% and 0.7% in navigation accuracy for unseen scenes, validating its effectiveness.

Gai Zhang, Xinfeng Zhang, Lv Tang et al.

Light field images capture multi-view scene information and play a crucial role in 3D scene reconstruction. However, their high-dimensional nature results in enormous data volumes, posing a significant challenge for efficient compression in practical storage and transmission scenarios. Although neural representation-based methods have shown promise in light field image compression, most approaches rely on direct coordinate-to-pixel mapping through implicit neural representation (INR), often neglecting the explicit modeling of scene structure. Moreover, they typically lack end-to-end rate-distortion optimization, limiting their compression efficiency. To address these limitations, we propose SANR, a Scene-Aware Neural Representation framework for light field image compression with end-to-end rate-distortion optimization. For scene awareness, SANR introduces a hierarchical scene modeling block that leverages multi-scale latent codes to capture intrinsic scene structures, thereby reducing the information gap between INR input coordinates and the target light field image. From a compression perspective, SANR is the first to incorporate entropy-constrained quantization-aware training (QAT) into neural representation-based light field image compression, enabling end-to-end rate-distortion optimization. Extensive experiment results demonstrate that SANR significantly outperforms state-of-the-art techniques regarding rate-distortion performance with a 65.62\% BD-rate saving against HEVC.

Jun Zhu, Xinfeng Zhang, Lv Tang et al.

Implicit Neural representations (INRs) have emerged as a promising approach for video compression, and have achieved comparable performance to the state-of-the-art codecs such as H.266/VVC. However, existing INR-based methods struggle to effectively represent detail-intensive and fast-changing video content. This limitation mainly stems from the underutilization of internal network features and the absence of video-specific considerations in network design. To address these challenges, we propose a multi-scale feature fusion framework, MSNeRV, for neural video representation. In the encoding stage, we enhance temporal consistency by employing temporal windows, and divide the video into multiple Groups of Pictures (GoPs), where a GoP-level grid is used for background representation. Additionally, we design a multi-scale spatial decoder with a scale-adaptive loss function to integrate multi-resolution and multi-frequency information. To further improve feature extraction, we introduce a multi-scale feature block that fully leverages hidden features. We evaluate MSNeRV on HEVC ClassB and UVG datasets for video representation and compression. Experimental results demonstrate that our model exhibits superior representation capability among INR-based approaches and surpasses VTM-23.7 (Random Access) in dynamic scenarios in terms of compression efficiency.

Bo Li, Haoke Xiao, Lv Tang

Vision Mamba has recently emerged as a promising alternative to Transformer-based architectures, offering linear complexity in sequence length while maintaining strong modeling capacity. However, its adaptation to visual inputs is hindered by challenges in 2D-to-1D patch serialization and weak scalability across input resolutions. Existing serialization strategies such as raster scanning disrupt local spatial continuity and limit the model's ability to generalize across scales. In this paper, we propose FractalMamba++, a robust vision backbone that leverages fractal-based patch serialization via Hilbert curves to preserve spatial locality and enable seamless resolution adaptability. To address long-range dependency fading in high-resolution inputs, we further introduce a Cross-State Routing (CSR) mechanism that enhances global context propagation through selective state reuse. Additionally, we propose a Positional-Relation Capture (PRC) module to recover local adjacency disrupted by curve inflection points. Extensive experiments across diverse downstream tasks, including image classification, semantic segmentation and object detection, demonstrate that FractalMamba++ consistently outperforms previous Mamba-based backbones, with particularly notable gains under high-resolution settings.

Yijie Zhong, Bo Li, Lv Tang et al.

Over the last few years, deep learning based approaches have achieved outstanding improvements in natural image matting. However, there are still two drawbacks that impede the widespread application of image matting: the reliance on user-provided trimaps and the heavy model sizes. In this paper, we propose a trimap-free natural image matting method with a lightweight model. With a lightweight basic convolution block, we build a two-stages framework: Segmentation Network (SN) is designed to capture sufficient semantics and classify the pixels into unknown, foreground and background regions; Matting Refine Network (MRN) aims at capturing detailed texture information and regressing accurate alpha values. With the proposed cross-level fusion Module (CFM), SN can efficiently utilize multi-scale features with less computational cost. Efficient non-local attention module (ENA) in MRN can efficiently model the relevance between different pixels and help regress high-quality alpha values. Utilizing these techniques, we construct an extremely light-weighted model, which achieves comparable performance with ~1\% parameters (344k) of large models on popular natural image matting benchmarks.

Lv Tang, Bo Li, Shouhong Ding et al.

Aiming at discovering and locating most distinctive objects from visual scenes, salient object detection (SOD) plays an essential role in various computer vision systems. Coming to the era of high resolution, SOD methods are facing new challenges. The major limitation of previous methods is that they try to identify the salient regions and estimate the accurate objects boundaries simultaneously with a single regression task at low-resolution. This practice ignores the inherent difference between the two difficult problems, resulting in poor detection quality. In this paper, we propose a novel deep learning framework for high-resolution SOD task, which disentangles the task into a low-resolution saliency classification network (LRSCN) and a high-resolution refinement network (HRRN). As a pixel-wise classification task, LRSCN is designed to capture sufficient semantics at low-resolution to identify the definite salient, background and uncertain image regions. HRRN is a regression task, which aims at accurately refining the saliency value of pixels in the uncertain region to preserve a clear object boundary at high-resolution with limited GPU memory. It is worth noting that by introducing uncertainty into the training process, our HRRN can well address the high-resolution refinement task without using any high-resolution training data. Extensive experiments on high-resolution saliency datasets as well as some widely used saliency benchmarks show that the proposed method achieves superior performance compared to the state-of-the-art methods.

Lv Tang, Bo Li

Co-Salient Object Detection (CoSOD) aims at simulating the human visual system to discover the common and salient objects from a group of relevant images. Recent methods typically develop sophisticated deep learning based models have greatly improved the performance of CoSOD task. But there are still two major drawbacks that need to be further addressed, 1) sub-optimal inter-image relationship modeling; 2) lacking consideration of inter-image separability. In this paper, we propose the Co-Salient Object Detection Transformer (CoSformer) network to capture both salient and common visual patterns from multiple images. By leveraging Transformer architecture, the proposed method address the influence of the input orders and greatly improve the stability of the CoSOD task. We also introduce a novel concept of inter-image separability. We construct a contrast learning scheme to modeling the inter-image separability and learn more discriminative embedding space to distinguish true common objects from noisy objects. Extensive experiments on three challenging benchmarks, i.e., CoCA, CoSOD3k, and Cosal2015, demonstrate that our CoSformer outperforms cutting-edge models and achieves the new state-of-the-art. We hope that CoSformer can motivate future research for more visual co-analysis tasks.

Lv Tang, Bo Li

Salient object detection (SOD) is a fundamental computer vision task. Recently, with the revival of deep neural networks, SOD has made great progresses. However, there still exist two thorny issues that cannot be well addressed by existing methods, indistinguishable regions and complex structures. To address these two issues, in this paper we propose a novel deep network for accurate SOD, named CLASS. First, in order to leverage the different advantages of low-level and high-level features, we propose a novel non-local cross-level attention (CLA), which can capture the long-range feature dependencies to enhance the distinction of complete salient object. Second, a novel cross-level supervision (CLS) is designed to learn complementary context for complex structures through pixel-level, region-level and object-level. Then the fine structures and boundaries of salient objects can be well restored. In experiments, with the proposed CLA and CLS, our CLASS net. consistently outperforms 13 state-of-the-art methods on five datasets.