Deep Texture-Aware Features for Camouflaged Object Detection

• Published in: IEEE transactions on circuits and systems for video technology Vol. 33; no. 3; pp. 1157 - 1167
• Main Authors: Ren, Jingjing, Hu, Xiaowei, Zhu, Lei, Xu, Xuemiao, Xu, Yangyang, Wang, Weiming, Deng, Zijun, Heng, Pheng-Ann
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Camouflaged object detection; Convolution; Covariance matrices; Data mining; deep features; Deep learning; Feature extraction; Modules; Object detection; Object recognition; Semantics; Texture; texture-aware
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2021.3126591

Camouflaged object detection is a challenging task that aims to identify objects having similar texture to the surroundings. This paper presents to amplify the subtle texture difference between camouflaged objects and the background for camouflaged object detection by formulating multiple texture-aware refinement modules to learn the texture-aware features in a deep convolutional neural network. The texture-aware refinement module computes the biased co-variance matrices of feature responses to extract the texture information, adopts an affinity loss to learn a set of parameter maps that help to separate the texture between camouflaged objects and the background, and leverages a boundary-consistency loss to explore the structures of object details. We evaluate our network on the benchmark datasets for camouflaged object detection both qualitatively and quantitatively. Experimental results show that our approach outperforms various state-of-the-art methods by a large margin.