Search papers, labs, and topics across Lattice.
This paper introduces the VCP-DCN, a novel depth collaborative network designed to enhance camouflaged object detection (COD) by effectively leveraging both RGB and depth modalities. The method addresses limitations in existing COD approaches by incorporating a Separable Prototype Embedding module for modality-specific feature learning, a Multi-modality Dual Attention module for improved cross-modal representation, and a Depth Adaptive Injection module for optimal feature fusion. Experimental results across three authoritative datasets show significant performance improvements, underscoring the model's ability to detect camouflaged objects more effectively than previous methods.
VCP-DCN reveals that leveraging depth-specific features can dramatically enhance the detection of camouflaged objects, outperforming traditional RGB-D methods.
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.
