用深度提示增强SAM，提升隐蔽目标检测精度
DGA-Net: Enhancing SAM with Depth Prompting and Graph-Anchor Guidance for Camouflaged Object Detection
- 引入密集深度提示，融合图像与深度信息生成统一引导信号
- 通过全局锚点和非局部路径，解决特征层级信息衰减问题
- 在COD任务上超越现有方法，适合需要精准分割的场景
为充分挖掘隐蔽目标检测（COD）中的深度线索，我们提出DGA-Net，一种基于新颖'深度提示'范式的专用框架，适配分割一切模型（SAM）。区别于依赖稀疏提示（如点或框）的现有方法，本方法构建并传播密集深度提示。具体地，提出跨模态图增强（CGE）模块，在异构图中融合RGB语义与深度几何，生成统一引导信号。此外，设计锚点引导细化（AGR）模块，通过建立全局锚点与直接非局部通路，将深层引导广播至浅层，缓解特征层次中的信息衰减，确保分割精确一致。定量与定性实验表明，所提DGA-Net优于当前最先进的COD方法。
原文摘要 · Abstract (English)
To fully exploit depth cues in Camouflaged Object Detection (COD), we present DGA-Net, a specialized framework that adapts the Segment Anything Model (SAM) via a novel ``depth prompting" paradigm. Distinguished from existing approaches that primarily rely on sparse prompts (e.g., points or boxes), our method introduces a holistic mechanism for constructing and propagating dense depth prompts. Specifically, we propose a Cross-modal Graph Enhancement (CGE) module that synthesizes RGB semantics and depth geometric within a heterogeneous graph to form a unified guidance signal. Furthermore, we design an Anchor-Guided Refinement (AGR) module. To counteract the inherent information decay in feature hierarchies, AGR forges a global anchor and establishes direct non-local pathways to broadcast this guidance from deep to shallow layers, ensuring precise and consistent segmentation. Quantitative and qualitative experimental results demonstrate that our proposed DGA-Net outperforms the state-of-the-art COD methods.
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。