IPNet: Polarization-based Camouflaged Object Detection via dual-flow network

Authors: Xin Wang, Jiajia Ding, Zhao Zhang, Junfeng Xu and Jun Gao.

Proposed Baseline

Training/Testing

The training and testing experiments are conducted using PyTorch with a single NVIDIA 3090ti GPU of 24 GB Memory.

Downloading necessary data:

The PCOD_1200 dataset can be found in this download link (Google Drive)

Four images with different polarization angles can be found in this download link (Google Drive).