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

TL;DR

This paper introduces DSS, a progressive, training-free framework for zero-shot camouflaged object segmentation that refines object proposals and selects optimal masks, achieving state-of-the-art results.

Contribution

The paper proposes the DSS mechanism, combining object discovery, segmentation refinement, and mask selection without training, improving zero-shot camouflaged object segmentation.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Effectively handles multiple-instance scenes.

Operates without training or supervision.

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.