paper-with-me

Papers Camouflaged Object Segmentation

“Camouflaged Object Segmentation” 태그가 달린 논문 52편 · 필터 해제

Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation

2026-02-23 · Yilong Yang, Jianxin Tian, Shengchuan Zhang, Liujuan Cao arxiv

Current zero-shot Camouflaged Object Segmentation methods typically employ a two-stage pipeline (discover-then-segment): using MLLMs to obtain visual prompts, followed by SAM segmentation. However, relying solely on MLLM…

Camouflaged Object Segmentation

Context-measure: Contextualizing Metric for Camouflage

2025-12-08 · Chen-Yang Wang, Gepeng Ji, Song Shao, Ming-Ming Cheng 외 arxiv

Camouflage relies heavily on context, but current metrics used in camouflaged object segmentation ignore contextual cues. We identify two major drawbacks of these metrics: first, the Dimension Flaw - a predicted foregrou…

Camouflaged Object Segmentation

Classifier-Centric Adaptive Framework for Open-Vocabulary Camouflaged Object Segmentation

2025-09-29 · Hanyu Zhang, Yiming Zhou, Jinxia Zhang arxiv

Open-vocabulary camouflaged object segmentation requires models to segment camouflaged objects of arbitrary categories unseen during training, placing extremely high demands on generalization capabilities. Through analys…

Camouflaged Object Segmentation

ArgusCogito: Chain-of-Thought for Cross-Modal Synergy and Omnidirectional Reasoning in Camouflaged Object Segmentation

2025-08-25 · Jianwen Tan, Huiyao Zhang, Rui Xiong, Han Zhou 외 arxiv

Camouflaged Object Segmentation (COS) poses a significant challenge due to the intrinsic high similarity between targets and backgrounds, demanding models capable of profound holistic understanding beyond superficial cue…

Camouflaged Object SegmentationMedical Image SegmentationScene Understanding

An Instance-Aware Prompting Framework for Training-free Camouflaged Object Segmentation

2025-08-09 · Chao Yin, Jide Li, Hang Yao, Xiaoqiang Li arxiv

Training-free Camouflaged Object Segmentation (COS) seeks to segment camouflaged objects without task-specific training, by automatically generating visual prompts to guide the Segment Anything Model (SAM). However, exis…

Camouflaged Object Segmentation

DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation

2025-06-29 · Jihun Kim, Hoyong Kwon, Hyeokjun Kweon, Wooseong Jeong 외

Interactive segmentation (IS) allows users to iteratively refine object boundaries with minimal cues, such as positive and negative clicks. While the Segment Anything Model (SAM) has garnered attention in the IS communit…

Camouflaged Object SegmentationInteractive SegmentationSegmentationSemantic Segmentation+1

Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models

2025-06-24 · Kai Zhao, Wubang Yuan, Zheng Wang, Guanyi Li 외

Open-Vocabulary Camouflaged Object Segmentation (OVCOS) seeks to segment and classify camouflaged objects from arbitrary categories, presenting unique challenges due to visual ambiguity and unseen categories.Recent appro…

Camouflaged Object SegmentationSegmentationSemantic Segmentation

Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation

2025-06-07 · Chao Yin, Hao Li, Kequan Yang, Jide Li 외

While promptable segmentation (\textit{e.g.}, SAM) has shown promise for various segmentation tasks, it still requires manual visual prompts for each object to be segmented. In contrast, task-generic promptable segmentat…

Camouflaged Object SegmentationFeature CorrelationImage CaptioningSegmentation+3

ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation

2025-04-10 · Wenqi Guo, Shan Du

Camouflaged object segmentation presents unique challenges compared to traditional segmentation tasks, primarily due to the high similarity in patterns and colors between camouflaged objects and their backgrounds. Effect…

Camouflaged Object SegmentationDefect DetectionLesion SegmentationOptical Flow Estimation+3

CamoSAM2: Motion-Appearance Induced Auto-Refining Prompts for Video Camouflaged Object Detection

2025-04-01 · Xin Zhang, Keren Fu, Qijun Zhao

The Segment Anything Model 2 (SAM2), a prompt-guided video foundation model, has remarkably performed in video object segmentation, drawing significant attention in the community. Due to the high similarity between camou…

Camouflaged Object Segmentationobject-detectionObject DetectionSemantic Segmentation+2

ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation with Zero-Shot Method

2025-03-30 · Unpublished 2025 3 · Wenqi Guo, Shan Du

Camouflaged object segmentation presents unique challenges compared to traditional segmentation tasks, primarily due to the high similarity in patterns and colors between camouflaged objects and their backgrounds. Effect…

Camouflaged Object SegmentationDefect DetectionLesion SegmentationOptical Flow Estimation+3

CamSAM2: Segment Anything Accurately in Camouflaged Videos

2025-03-25 · Yuli Zhou, Guolei Sun, Yawei Li, Yuqian Fu 외

Video camouflaged object segmentation (VCOS), aiming at segmenting camouflaged objects that seamlessly blend into their environment, is a fundamental vision task with various real-world applications. With the release of …

Camouflaged Object SegmentationObjectSemantic SegmentationVideo Segmentation+1

Integrating Extra Modality Helps Segmentor Find Camouflaged Objects Well

2025-02-20 · Chengyu Fang, Chunming He, Longxiang Tang, Yuelin Zhang 외

Camouflaged Object Segmentation (COS) remains challenging because camouflaged objects exhibit only subtle visual differences from their backgrounds and single-modality RGB methods provide limited cues, leading researcher…

Camouflaged Object SegmentationSegmentationSemantic Segmentation

FOCUS: Towards Universal Foreground Segmentation

2025-01-09 · Zuyao You, Lingyu Kong, Lingchen Meng, Zuxuan Wu

Foreground segmentation is a fundamental task in computer vision, encompassing various subdivision tasks. Previous research has typically designed task-specific architectures for each task, leading to a lack of unificati…

Camouflaged Object SegmentationDefocus Blur DetectionForeground SegmentationSalient Object Detection+2

Camouflage Anything: Learning to Hide using Controlled Out-painting and Representation Engineering

2025-01-01 · CVPR 2025 1 · Biplab Das, Viswanath Gopalakrishnan

In this work, we introduce Camouflage Anything, a novel and robust approach to generate camouflaged datasets. To the best of our knowledge, we are the first to apply Controlled Out-painting and Representation Enginee…

Camouflaged Object SegmentationObjectSemantic Segmentation

Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotations

2024-10-22 · Cheng Lei, Jie Fan, Xinran Li, Tianzhu Xiang 외

Camouflaged Object Segmentation (COS) faces significant challenges due to the scarcity of annotated data, where meticulous pixel-level annotation is both labor-intensive and costly, primarily due to the intricate object-…

Camouflaged Object SegmentationLarge Language ModelMultimodal Large Language ModelNavigate+3

When SAM2 Meets Video Camouflaged Object Segmentation: A Comprehensive Evaluation and Adaptation

2024-09-27 · Yuli Zhou, Guolei Sun, Yawei Li, Guo-Sen Xie 외

This study investigates the application and performance of the Segment Anything Model 2 (SAM2) in the challenging task of video camouflaged object segmentation (VCOS). VCOS involves detecting objects that blend seamlessl…

Camouflaged Object SegmentationSemantic Segmentation

Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation

2024-08-27 · Jian Hu, Jiayi Lin, Junchi Yan, Shaogang Gong

Promptable segmentation typically requires instance-specific manual prompts to guide the segmentation of each desired object. To minimize such a need, task-generic promptable segmentation has been introduced, which emplo…

Camouflaged Object SegmentationCamouflaged Object Segmentation with a Single Task-generic PromptMedical Image SegmentationSegmentation

Unlocking Attributes' Contribution to Successful Camouflage: A Combined Textual and VisualAnalysis Strategy

2024-08-22 · Hong Zhang, Yixuan Lyu, Qian Yu, Hanyang Liu 외

In the domain of Camouflaged Object Segmentation (COS), despite continuous improvements in segmentation performance, the underlying mechanisms of effective camouflage remain poorly understood, akin to a black box. To add…

AttributeCamouflaged Object SegmentationSemantic Segmentation

Learning Camouflaged Object Detection from Noisy Pseudo Label

2024-07-18 · Jin Zhang, Ruiheng Zhang, Yanjiao Shi, Zhe Cao 외

Existing Camouflaged Object Detection (COD) methods rely heavily on large-scale pixel-annotated training sets, which are both time-consuming and labor-intensive. Although weakly supervised methods offer higher annotation…

Camouflaged Object SegmentationMemorizationObjectobject-detection+3
1–20 / 52 다음 →