Camouflaged Object Segmentation with Distraction Mining

TL;DR

This paper introduces PFNet, a bio-inspired framework for camouflaged object segmentation that mimics predation, utilizing a distraction mining strategy to improve accuracy and real-time performance.

Contribution

The paper proposes a novel bio-inspired PFNet with distraction mining for improved camouflaged object segmentation, achieving real-time speed and superior accuracy.

Findings

PFNet runs at 72 FPS in real-time.

Outperforms 18 state-of-the-art models on three datasets.

Uses distraction mining to enhance segmentation accuracy.

Abstract

Camouflaged object segmentation (COS) aims to identify objects that are "perfectly" assimilate into their surroundings, which has a wide range of valuable applications. The key challenge of COS is that there exist high intrinsic similarities between the candidate objects and noise background. In this paper, we strive to embrace challenges towards effective and efficient COS. To this end, we develop a bio-inspired framework, termed Positioning and Focus Network (PFNet), which mimics the process of predation in nature. Specifically, our PFNet contains two key modules, i.e., the positioning module (PM) and the focus module (FM). The PM is designed to mimic the detection process in predation for positioning the potential target objects from a global perspective and the FM is then used to perform the identification process in predation for progressively refining the coarse prediction via focusing on the ambiguous regions. Notably, in the FM, we develop a novel distraction mining strategy for distraction discovery and removal, to benefit the performance of estimation. Extensive experiments demonstrate that our PFNet runs in real-time (72 FPS) and significantly outperforms 18 cutting-edge models on three challenging datasets under four standard metrics.