Deep Texture-Aware Features for Camouflaged Object Detection

Abstract

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 covariance matrices of feature responses to extract the texture information, designs an affinity loss to learn a set of parameter maps that help to separate the texture between camouflaged objects and the background, and adopts a boundary-consistency loss to explore the object detail structures. We evaluate our network on the benchmark dataset 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.

Deep Gradient Learning for Efficient Camouflaged Object Detection

“…To mimic the detection process of predators, Mei et al [11] develop PFNet, which contains a positioning and focusing module to conduct the identification. [16,27] propose delicate structures such as covariance matrices of feature and multivariate calibration components to improve the robustness of the network. Kajiura et al [28] improve the detection accuracy via exploring the uncertainties of pseudoedge and pseudo-map labels.…”