HDPNet: Hourglass Vision Transformer with Dual-Path Feature Pyramid for Camouflaged Object Detection

Existing camouflaged object detection methods often struggle with detecting small objects and fine object bound-aries. To alleviate these issues, we propose a novel hour-glass vision Transformer with Dual-path Feature Pyramid (HDPNet). Specifically, we construct an hourglass Trans-former encoder that effectively captures the global semantic cues while extracting detailed feature maps at vari-ous scales, preserving the spatial details and fine-grained boundaries of the camouflaged object. To ensure the preser-vation of essential cues of hourglass features, we introduce a dual-pathfeature pyramid decoder (DPFD). This decoder performs coarse-to-fine feature fusion laterally, mitigating the dilution of essential feature cues caused by the semantic gaps. In addition, to further facilitate the local feature modeling in the encoder to mine the correlation between local features and global semantic cues from the camou-flaged region, we design a feature interaction enhancement module (FIEM). This module adopts a symmetric structure enables detailed appearance features and global se-mantic features to complement each other, enhancing the model's ability to capture a wide range of fine-grained details. Extensive quantitative and qualitative experiments demonstrate that the proposed model significantly outper-forms 25 existing methods across three challenging COD benchmark datasets, particularly excelling in the detection of small objects and fine boundaries. The code is available at https://github.com/LittleGrey-hjpIHDPNet.