DGA-Net: Enhancing SAM with Depth Prompting and Graph-Anchor Guidance for Camouflaged Object Detection

TL;DR

DGA-Net enhances camouflaged object detection by integrating depth prompts and graph-based guidance into SAM, significantly improving segmentation accuracy through novel modules that leverage depth cues and global anchors.

Contribution

Introduces a depth prompting paradigm and novel modules CGE and AGR to improve SAM's performance on camouflaged object detection.

Findings

Outperforms state-of-the-art COD methods quantitatively.

Effectively utilizes depth cues for better segmentation.

Provides a holistic framework for dense depth prompt propagation.

Abstract

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.