Seamless Detection: Unifying Salient Object Detection and Camouflaged Object Detection
School of Computer Science and Artificial Intelligence, Changzhou University（常州大学计算机科学与人工智能学院）；School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）；Department of Automation, Tsinghua University（清华大学自动化系）
Yi Liu, Chengxin Li, Xiaohui Dong, Lei Li, Dingwen Zhang, Shoukun Xu, Jungong Han
Achieving joint learning of Salient Object Detection (SOD) and Camouflaged Object Detection (COD) is extremely challenging due to their distinct object characteristics, i.e., saliency and camouflage. The only preliminary research treats them as two contradictory tasks, training models on large-scale labeled data alternately for each task and assessing them independently. However, such task-specific mechanisms fail to meet real-world demands for addressing unknown tasks effectively. To address this issue, in this paper, we pioneer a task-agnostic framework to unify SOD and COD. To this end, inspired by the agreeable nature of binary segmentation for SOD and COD, we propose a Contrastive Distillation Paradigm (CDP) to distil the foreground from the background, facilitating the identification of salient and camouflaged objects amidst their surroundings. To probe into the contribution of our CDP, we design a simple yet effective contextual decoder involving the interval-layer and global context, which achieves an inference speed of 67 fps. Besides the supervised setting, our CDP can be seamlessly integrated into unsupervised settings, eliminating the reliance on extensive human annotations. Experiments on public SOD and COD datasets demonstrate the superiority of our proposed framework in both supervised and unsupervised settings, compared with existing state-of-the-art approaches. Code is available on https://github.com/liuyi1989/Seamless-Detection.
Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes
School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件工程学院）；School of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程学院）；School of Computer Science and Technology, Hainan University（海南大学计算机科学与技术学院）
Northwestern Polytechnical University（西北工业大学）；Australian National University（澳大利亚国立大学）；CSIRO（澳大利亚联邦科学与工业研究组织）；EPFL（瑞士洛桑联邦理工学院）
Visual salient object detection (SOD) aims at finding the salient object(s) that attract human attention, while camouflaged object detection (COD) on the contrary intends to discover the camouflaged object(s) that hidden in the surrounding. In this paper, we propose a paradigm of leveraging the contradictory information to enhance the detection ability of both salient object detection and camouflaged object detection. We start by exploiting the easy positive samples in the COD dataset to serve as hard positive samples in the SOD task to improve the robustness of the SOD model. Then, we introdu…
Distribution-Specific Learning for Joint Salient and Camouflaged Object Detection
School of Computing and Information Technology, Great Bay University（计算与信息学院，大湾大学）；Computer Vision and Pattern Recognition Laboratory, School of Engineering Science, Lappeenranta-Lahti University of Technology LUT（计算机视觉与模式识别实验室，工程科学学院，拉佩兰塔-拉赫蒂技术大学）；School of Computer Science and Software Engineering, Shenzhen University（计算机科学与软件工程学院，深圳大学）；School of Software Engineering, Xi’an Jiaotong University（软件工程学院，西安交通大学）；School of Electrical and Information Engineering, Tianjin University（电气与信息工程学院，天津大学）
VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning
Northwestern Polytechnical University（西北工业大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；National University of Singapore（新加坡国立大学）；Nankai University（南开大学）；Nankai International Advanced Research Institute (SHENZHEN FUTIAN)（南开大学深圳福田国际高级研究院）；Linköping University（林雪平大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Referring Camouflaged Object Detection With Multi-Context Overlapped Windows Cross-Attention
School of Computer and Information Engineering, Shanghai Polytechnic University（计算机与信息工程学院，上海理工大学）；Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University（智能信息处理重点实验室，复旦大学）；Department of Automation, School of Intelligent Manufacturing and Control Engineering, Shanghai Polytechnic University（自动化系，智能制造与控制工程学院，上海理工大学）；Academy for Engineering and Technology, Fudan University（工程与技术学院，复旦大学）；Research and Design Center, Shanghai Insititue Of Computer Technology Company（研发设计中心，上海计算机技术有限公司）
HVPNet: A Bio-Inspired Network for General Salient and Camouflaged Object Detection
School of Artificial Intelligence, Jiangxi Normal University（江西师范大学人工智能学院）；Faculty of Business Information, Shanghai Business School（上海商学院商务信息学院）；School of Computer Science and Information Engineering, Shanghai Institute of Technology（上海应用技术大学计算机科学与信息工程学院）
Tencent Youtu Lab（腾讯优图实验室）；ETH Zurich（苏黎世联邦理工学院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Sun Yat-sen University（中山大学）
Spotting camouflaged objects that are visually assimilated into the background is tricky for both object detection algorithms and humans who are usually confused or cheated by the perfectly intrinsic similarities between the foreground objects and the background surroundings. To tackle this challenge, we aim to extract the high-resolution texture details to avoid the detail degradation that causes blurred vision in edges and boundaries. We introduce a novel HitNet to refine the low-resolution representations by high-resolution features in an iterative feedback manner, essentially a global loop…
Assisted Refinement Network Based on Channel Information Interaction for Camouflaged and Salient Object Detection
Department of Physics, J.K. Institute of Science（物理系，J.K.科学研究院）；World Scientific University（世界科学大学）；University of Intelligent Studies（智能研究大学）；School of Computer Science and Technology, Xinjiang University（计算机科学与技术学院，新疆大学）；Department of Electronic Engineering, Tsinghua University（电子工程系，清华大学）
A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detection
School of Electrical and Information Engineering, Tianjin University（天津大学电气与信息工程学院）；School of Computing and Information Technology, Great Bay University（湾区大学计算与信息技术学院）；Computer Vision and Pattern Recognition Laboratory, Lappeenranta-Lahti University of Technology LUT（拉彭兰塔-拉赫蒂理工大学计算机视觉与模式识别实验室）；School of Statistics and Data Science, Nankai University（南开大学统计与数据科学学院）
本文提出基于 ViT 的简单非对称编解码网络 SENet，结合 LICM 与动态加权损失，并解决 COD/SOD 联合训练冲突，在两类检测任务上均取得有竞争力的性能。
School of Computer Science, Nankai University（南开大学计算机学院）；BNRist, Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系BNRist（注：BNRist为北京信息科学与技术国家研究中心的英文缩写））
FocusDiffuser: Perceiving Local Disparities for Camouflaged Object Detection
University of Electronic Science and Technology of China（电子科技大学）；Group 42 (G42)（G42集团）；Sichuan Agricultural University（四川农业大学）；Southwest Jiaotong University（西南交通大学）；Brown University（布朗大学）
Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection
Information Science and Technology College, Dalian Maritime University（大连海事大学信息科学与技术学院）；Beijing University of Technology（北京理工大学）；Dalian University of Technology（大连理工大学）
Hierarchical Graph Interaction Transformer with Dynamic Token Clustering for Camouflaged Object Detection
School of Computer Science (National Pilot Software Engineering School), Beijing University Of Posts and Telecommunications（北京邮电大学计算机学院（国家示范性软件学院））；Inception Institute of Artificial Intelligence（Inception人工智能研究院）；G42 Bayanat（G42巴亚纳特公司）；School of Software, Beihang University（北京航空航天大学软件学院）；School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University（中山大学深圳校区网络空间安全学院）
University of Chinese Academy of Sciences（中国科学院大学）；Sun Yat-Sen University（中山大学）；Tsinghua University（清华大学）
Camouflaged objects are seamlessly blended in with their surroundings, which brings a challenging detection task in computer vision. Optimizing a convolutional neural network (CNN) for camouflaged object detection (COD) tends to activate local discriminative regions while ignoring complete object extent, causing the partial activation issue which inevitably leads to missing or redundant regions of objects. In this paper, we argue that partial activation is caused by the intrinsic characteristics of CNN, where the convolution operations produce local receptive fields and experience difficulty t…
Just a Hint: Point-Supervised Camouflaged Object Detection
Unmanned System Research Institute, Northwestern Polytechnical University（西北工业大学无人系统研究院）；National Key Laboratory of Unmanned Aerial Vehicle Technology（无人机技术国家重点实验室）
C3Net: Context-Contrast Network for Camouflaged Object Detection
Computer Engineering Department, King Fahd University of Petroleum and Minerals（国王法赫德石油和矿物大学计算机工程系）；Electronic Systems Engineering, University of Regina（里贾纳大学电子系统工程系）；Department of Computer Science and Software Engineering, The University of Western Australia（西澳大学计算机科学与软件工程系）
MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection
King Fahd University of Petroleum and Minerals（国王法赫德石油与矿物大学）；Ontario Tech University（安大略技术大学）；National University of Computer and Emerging Sciences（国家计算机与新兴科学大学）；The University of Regina（里贾纳大学）；The University of Western Australia（西澳大学）
A Survey of Camouflaged Object Detection and Beyond
Tsinghua University（清华大学）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Peking University（北京大学）；School of Electrical and Computer Engineering, Peking University（北京大学电气与计算机工程学院）；Duke University（杜克大学）
DualGazeNet: A Biologically Inspired Dual-Gaze Query Network for Salient Object Detection
School of Computation, Information and Technology, Technical University of Munich（计算信息与技术学院，慕尼黑技术大学）；Department of Informatics, Technical University of Munich（信息学院，慕尼黑技术大学）；University Research and Innovation Center, Obuda University（奥布达大学研究与创新中心）；State Key Laboratory for Novel Software Technology, Nanjing University Suzhou Campus（新型软件技术国家重点实验室，南京大学苏州校区）；School of Science and Technology, Nanjing University Suzhou Campus（科学与技术学院，南京大学苏州校区）；Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）
We solve the problem of salient object detection by investigating how to expand the role of pooling in convolutional neural networks. Based on the U-shape architecture, we first build a global guidance module (GGM) upon the bottom-up pathway, aiming at providing layers at different feature levels the location information of potential salient objects. We further design a feature aggregation module (FAM) to make the coarse-level semantic information well fused with the fine-level features from the top-down pathway. By adding FAMs after the fusion operations in the top-down pathway, coarse-level …
HyPSAM: Hybrid Prompt-driven Segment Anything Model for RGB-Thermal Salient Object Detection
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；School of Information Science and Engineering, Yunnan University（云南大学信息科学与工程学院）；School of Mathematics, Southeast University（东南大学数学学院）
We present a systematic study on a new task called dichotomous image segmentation (DIS) , which aims to segment highly accurate objects from natural images. To this end, we collected the first large-scale DIS dataset, called DIS5K, which contains 5,470 high-resolution (e.g., 2K, 4K or larger) images covering camouflaged, salient, or meticulous objects in various backgrounds. DIS is annotated with extremely fine-grained labels. Besides, we introduce a simple intermediate supervision baseline (IS-Net) using both feature-level and mask-level guidance for DIS model training. IS-Net outperforms var…
College of Computer Science and Engineering, Guilin University of Technology, China（桂林理工大学计算机科学与工程学院）；Guangxi Key Laboratory of Embedded Technology and Intelligent System, Guilin University of Technology, China（广西嵌入式技术与智能系统重点实验室）；School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China（西安交通大学自动化科学与工程学院）；College of Computer Science, Sichuan University, Sichuan 610065, China（四川大学计算机学院）
SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Computer and Information Engineering, Jiangxi Normal University（江西师范大学计算机与信息工程学院）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Tianjin University（天津大学）；Monash University（墨尔本大学）；Pazhou Lab（琶洲实验室）；Smart Hospital Research Institute, Peking University Shenzhen Hospital（北京大学深圳医院智能医院研究所）
ETH Zurich（苏黎世联邦理工学院）；University of Burgundy（勃艮第大学）；CNRS（法国国家科学研究中心）；University of Wurzburg（维尔茨堡大学）；Sofia University（索非亚大学）；INSAIT（计算机科学与人工智能研究所）；AUST（安徽理工大学）；University of Lorraine（洛林大学）；Inria（法国国家信息与自动化研究所）
University of Alberta（阿尔伯塔大学）；Inception Institute of Artificial Intelligence (IIAI)（人工智能 inception 研究所）；Init ML；Polytechnic University of Catalonia, BarcelonaTech（加泰罗尼亚理工大学）
Although deep models have greatly improved the accuracy and robustness of image segmentation, obtaining segmentation results with highly accurate boundaries and fine structures is still a challenging problem. In this paper, we propose a simple yet powerful Boundary-Aware Segmentation Network (BASNet), which comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation. The predict-refine architecture consists of a densely supervised encoder-decoder network and a residual refinement module, which are respectively used to predict and refine a segmentation prob…
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；CVL, ETH Zurich（苏黎世联邦理工学院计算机视觉实验室）；School of Computer Science and Engineering, Northwestern Polytechnical University（西北工业大学计算机科学与工程学院）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究院）
Salient object detection (SOD) on RGB and depth images has attracted more and more research interests, due to its effectiveness and the fact that depth cues can now be conveniently captured. Existing RGB-D SOD models usually adopt different fusion strategies to learn a shared representation from the two modalities (\ie, RGB and depth), while few methods explicitly consider how to preserve modality-specific characteristics. In this study, we propose a novel framework, termed SPNet} (Specificity-preserving network), which benefits SOD performance by exploring both the shared information and moda…
LSP-ST: Ladder Shape-Biased Side-Tuning for Robust Infrared Small Target Detection
School of Aeronautics and Astronautics, Sun Yat-sen University（航空宇航学院，中山大学）；Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences（长春光学精密机械与物理研究所，中国科学院）
针对基础模型纹理偏置导致红外小目标检测泛化性差的问题，提出 LSP-ST 侧边微调方法，通过引入全局形状结构先验和形状增强大核注意力模块，仅用 4.72M 参数即在多基准上达到 SOTA 且泛化性优异。
Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach
School of Computer Science and Technology, University of Chinese Academy of Sciences（计算机科学与技术学院，中国科学院大学）；State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences（人工智能安全国家重点实验室，中国科学院计算技术研究所）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；School of Cyber Security, University of Chinese Academy of Sciences（网络安全学院，中国科学院大学）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（网络安全科学与技术学院，中山大学深圳校区）
When SAM2 Meets Video Camouflaged Object Segmentation: A Comprehensive Evaluation and Adaptation
Computer Vision Laboratory, ETH Zürich（苏黎世联邦理工学院计算机视觉实验室）；Integrated System Laboratory, ETH Zürich（苏黎世联邦理工学院集成系统实验室）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）
University of Central Florida（中佛罗里达大学）；Microsoft Dynamics 365 AI Research（微软 Dynamics 365 AI 研究院）
We propose a new task towards more practical application for image generation - high-quality image synthesis from salient object layout. This new setting allows users to provide the layout of salient objects only (i.e., foreground bounding boxes and categories), and lets the model complete the drawing with an invented background and a matching foreground. Two main challenges spring from this new task: (i) how to generate fine-grained details and realistic textures without segmentation map input; and (ii) how to create a background and weave it seamlessly into standalone objects. To tackle this…
Effectiveness Assessment of Recent Large Vision-Language Models
Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Sichuan University（四川大学）；Tianjin University（天津大学）；Australian National University（澳大利亚国立大学）；Harbin Institute of Technology（哈尔滨工业大学）；Nankai University（南开大学）
