Polarization-based Camouflaged Object Detection with high-resolution adaptive fusion Network

Abstract

In comparison to traditional object detection or segmentation tasks, Camouflaged Object Detection (COD) poses greater challenges, as humans are often perplexed or deceived by the inherent similarities between foreground objects and their background surroundings. Polarization information serves as a valuable asset for discerning the attributes of objects with varied characteristics and surface texture. Taking inspiration from the polarization vision systems observed in animals, this study presents the High-Resolution Intensity & Polarization Fusion (HIPF) Net, a high-efficiency cross-modal fusion network that leverages trichromatic intensity and linear orthogonal polarization cues to produce a scene representation that is rich in texture and edge details. Specifically, the Early Adaptive Stokes Fusion (EASF) module maximizes the utilization of information from linear orthogonal polarization images. Subsequently, the Mix-Attention Feature Interaction Module (MAI) is introduced to facilitate complementary interaction among low-level features. Additionally, the Attentional Receptive Field Block (ARFB) enables the model to uncover concealed cues effectively, capturing objects of various sizes. Finally, the Weighted Cross-Level Decoder(WCFD) is designed to dynamically fuse and assign weights to cross-level contextual information for robust detection. Training and extensive validation of our model are performed on the polarization-based dataset as well as non-polarization-based datasets, with experimental results demonstrating that HIPFNet consistently outperforms state-of-the-art methods. Source codes are available at https://github.com/CVhfut/HIPFNet.