DGA-Net: Enhancing SAM with Depth Prompting and Graph-Anchor Guidance for Camouflaged Object Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908749847855104 |
|---|---|
| author | Li, Yuetong Zhang, Qing Zhao, Yilin Li, Gongyang Liu, Zeming |
| author_facet | Li, Yuetong Zhang, Qing Zhao, Yilin Li, Gongyang Liu, Zeming |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_02831 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DGA-Net: Enhancing SAM with Depth Prompting and Graph-Anchor Guidance for Camouflaged Object Detection Li, Yuetong Zhang, Qing Zhao, Yilin Li, Gongyang Liu, Zeming Computer Vision and Pattern Recognition 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. |
| title | DGA-Net: Enhancing SAM with Depth Prompting and Graph-Anchor Guidance for Camouflaged Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.02831 |