This paper introduces DGNet, a novel deep framework that exploits object gradient supervision for camouflaged object detection (COD). It decouples the task into two connected branches, i.e., a context and a texture encoder. The essential connection is the gradient-induced transition, representing a soft grouping between context and texture features. Benefiting from the simple but efficient framework, DGNet outperforms existing state-of-the-art COD models by a large margin. Notably, our efficient version, DGNet-S, runs in real-time (80 fps) and achieves comparable results to the cutting-edge model JCSOD-CVPR21 with only 6.82% parameters. Application results also show that the proposed DGNet performs well in polyp segmentation, defect detection, and transparent object segmentation tasks. Codes will be made available at https://github.com/GewelsJI/DGNet.
@article{arxiv.2205.12853,
title = {Deep Gradient Learning for Efficient Camouflaged Object Detection},
author = {Ge-Peng Ji and Deng-Ping Fan and Yu-Cheng Chou and Dengxin Dai and Alexander Liniger and Luc Van Gool},
journal= {arXiv preprint arXiv:2205.12853},
year = {2023}
}