提出渐进式方法DSS，提升隐身物体分割精度
Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation
- 分三步渐进处理：发现、分割、选择，逐层优化
- 在多实例场景下表现最优，零样本无训练
- 适合需要高精度隐身目标分割的研究者
现有零样本隐身物体分割方法通常采用发现-分割两阶段流程：先用多模态大模型（MLLM）生成视觉提示，再通过SAM进行分割。然而，仅依赖MLLM进行发现常导致定位不准、误检和漏检。为此，我们提出发现-分割-选择（DSS）机制，一种逐步精炼的框架。该方法包含特征一致的物体发现（FOD）模块，利用视觉特征生成多样化的物体候选；分割模块通过SAM对候选进行细化；以及语义驱动的掩码选择（SMS）模块，利用MLLM评估并选出最佳分割结果。无需任何训练或监督，DSS在多个COS基准上达到领先性能，尤其在多实例场景中表现突出。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。