VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection

2026-07-30

AI Summary

This work addresses the limitation of existing camouflaged object detection methods that overlook the modality-specific characteristics of camouflaged objects in depth data, thereby hindering effective multimodal collaboration. To overcome this, we propose a Depth-Collaborative Network (VCP-DCN) that disentangles prototype embeddings to separately model modality-shared and modality-specific features. The network integrates a multimodal dual-attention mechanism to enhance cross-modal local responses and introduces a depth-adaptive injection module for efficient feature fusion. Extensive experiments on three benchmark RGB-D camouflaged object detection datasets demonstrate that our method significantly outperforms state-of-the-art approaches, confirming its effectiveness and robustness.

Abstract

Camouflaged Object Detection (COD) aims to identify and segment camouflaged objects in complex environments, which are often concealed because their color and texture are similar to the background. Several existing COD methods introduce depth maps to boost detection performance via learning complementary RGB-D features, ignoring modality-specific characteristics of concealed objects in the depth domain. To address this issue, we propose a depth collaborative network, called VCP-DCN, to mine distinguishable multi-modality features beyond visual concealed prototype in depth domain. Specifically, VCP-DCN progressively performs multi-modality alignment, interaction, and fusion for the COD task. In the \textbf{alignment} stage, we propose a Separable Prototype Embedding (SPE) module to learn modality-consistency and modality-specific RGB/depth prototype tokens through prototype contrastive learning. Furthermore, we develop a Multi-modality Dual Attention (MDA) module to enhance the cross-modal feature representation through local response maps between modality-consistency RGB/depth prototype tokens and visual tokens on the \textbf{interaction} stage. Finally, we design a Depth Adaptive Injection (DAI) module to adaptively measure contribution of RGB/depth features with a decision-making mechanism, which calculates similarity distance between RGB/depth modality-specific prototype tokens and modality-consistency ones on the \textbf{fusion} stage. Extensive experiments demonstrate the effectiveness of our VCP-DCN on three authoritative datasets.

Problem

• Camouflaged Object Detection
• depth modality
• modality-specific characteristics
• RGB-D features
• visual concealed property

Innovation

• Camouflaged Object Detection
• Depth Collaborative Network
• Prototype Contrastive Learning
• Multi-modality Fusion
• Modality-specific Features