TINYCOD: Tiny and Effective Model for Camouflaged Object Detection

Haozhe Xing, Shuyong Gao, Hao Tang, Tsui Qin Mok, Yanlan Kang, Wenqiang Zhang

Abstract

This paper introduces an effective and tiny model for real-time Camouflaged Object Detection (COD) named Tiny-COD. It achieves high performance with very low costs (Parameters < 5M, FLOPs < 1.5G), which can be applied on mobile devices. Specifically, we introduce a simple but effective Adjacent Scale Features Fusion module (ASFF), which can significantly enhance the representation ability of features from a lightweight backbone. Besides, as the edge areas of the camouflaged object often blend into the background, we carefully design an Edge Area Focus module (EAF) to solve this problem. Experimental results on COD datasets prove that the proposed method achieves state-of-the-art performance compared with other methods.
BibTeX
@inproceedings{xing2023tinycod,
  author = {Haozhe Xing and Shuyong Gao and Hao Tang and Tsui Qin Mok and Yanlan Kang and Wenqiang Zhang},
  title = {{TINYCOD: Tiny and Effective Model for Camouflaged Object Detection}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2023},
  doi = {10.1109/icassp49357.2023.10095226},
}

Loading related content...

Figure