Deep Texture-Aware Features for Camouflaged Object Detection

TL;DR

This paper introduces a deep learning approach that enhances texture differences to improve camouflaged object detection, significantly outperforming existing methods on benchmark datasets.

Contribution

It proposes multiple texture-aware refinement modules that utilize covariance matrices, affinity loss, and boundary-consistency loss to better distinguish camouflaged objects from backgrounds.

Findings

Outperforms state-of-the-art methods by a large margin

Effectively captures subtle texture differences

Achieves superior results on benchmark datasets

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.