Camouflaged Object Segmentation with Distraction Mining

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.

CVPR 2021

References in corpus (15)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• ParseNet: Looking Wider to See Better
• Anabranch Network for Camouflaged Object Segmentation
• Deeply supervised salient object detection with short connections
• Direction-aware Spatial Context Features for Shadow Detection
• Deep Learning for Generic Object Detection: A Survey
• Hybrid Task Cascade for Instance Segmentation
• DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factors
• Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
• Structure-measure: A New Way to Evaluate Foreground Maps
• Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
• Distractor-aware Siamese Networks for Visual Object Tracking
• Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground
• Semantic Segmentation with Reverse Attention

Cited by in corpus (3)

• Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
• Advances in Deep Concealed Scene Understanding
• Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels