Research

Paper

AI LLM February 23, 2026

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

Authors

Yilong Yang, Jianxin Tian, Shengchuan Zhang, Liujuan Cao

Abstract

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 MLLMs for camouflaged object discovery often leads to inaccurate localization, false positives, and missed detections. To address these issues, we propose the \textbf{D}iscover-\textbf{S}egment-\textbf{S}elect (\textbf{DSS}) mechanism, a progressive framework designed to refine segmentation step by step. The proposed method contains a Feature-coherent Object Discovery (FOD) module that leverages visual features to generate diverse object proposals, a segmentation module that refines these proposals through SAM segmentation, and a Semantic-driven Mask Selection (SMS) module that employs MLLMs to evaluate and select the optimal segmentation mask from multiple candidates. Without requiring any training or supervision, DSS achieves state-of-the-art performance on multiple COS benchmarks, especially in multiple-instance scenes.

Metadata

arXiv ID: 2602.19944
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-02-23
Fetched: 2026-02-24 04:38

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.19944v1</id>\n    <title>Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation</title>\n    <updated>2026-02-23T15:15:37Z</updated>\n    <link href='https://arxiv.org/abs/2602.19944v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.19944v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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 MLLMs for camouflaged object discovery often leads to inaccurate localization, false positives, and missed detections. To address these issues, we propose the \\textbf{D}iscover-\\textbf{S}egment-\\textbf{S}elect (\\textbf{DSS}) mechanism, a progressive framework designed to refine segmentation step by step. The proposed method contains a Feature-coherent Object Discovery (FOD) module that leverages visual features to generate diverse object proposals, a segmentation module that refines these proposals through SAM segmentation, and a Semantic-driven Mask Selection (SMS) module that employs MLLMs to evaluate and select the optimal segmentation mask from multiple candidates. Without requiring any training or supervision, DSS achieves state-of-the-art performance on multiple COS benchmarks, especially in multiple-instance scenes.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-02-23T15:15:37Z</published>\n    <arxiv:comment>Accepted by CVPR 2026 (main conference)</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Yilong Yang</name>\n    </author>\n    <author>\n      <name>Jianxin Tian</name>\n    </author>\n    <author>\n      <name>Shengchuan Zhang</name>\n    </author>\n    <author>\n      <name>Liujuan Cao</name>\n    </author>\n  </entry>"
}