Anabranch Network for Camouflaged Object Segmentation

TL;DR

This paper introduces the Anabranch Network, a novel end-to-end deep learning model that improves camouflaged object segmentation by integrating classification and segmentation tasks, supported by a new dataset and extensive experiments.

Contribution

The paper presents a new network architecture with a classification branch for camouflaged object detection, enhancing segmentation accuracy over existing methods.

Findings

Effective segmentation of camouflaged objects demonstrated on the new dataset.

The classification branch improves segmentation performance.

The approach outperforms existing segmentation networks on the benchmark.

Abstract

Camouflaged objects attempt to conceal their texture into the background and discriminating them from the background is hard even for human beings. The main objective of this paper is to explore the camouflaged object segmentation problem, namely, segmenting the camouflaged object(s) for a given image. This problem has not been well studied in spite of a wide range of potential applications including the preservation of wild animals and the discovery of new species, surveillance systems, search-and-rescue missions in the event of natural disasters such as earthquakes, floods or hurricanes. This paper addresses a new challenging problem of camouflaged object segmentation. To address this problem, we provide a new image dataset of camouflaged objects for benchmarking purposes. In addition, we propose a general end-to-end network, called the Anabranch Network, that leverages both classification and segmentation tasks. Different from existing networks for segmentation, our proposed network possesses the second branch for classification to predict the probability of containing camouflaged object(s) in an image, which is then fused into the main branch for segmentation to boost up the segmentation accuracy. Extensive experiments conducted on the newly built dataset demonstrate the effectiveness of our network using various fully convolutional networks. \url{https://sites.google.com/view/ltnghia/research/camo}