MirrorNet: Bio-Inspired Camouflaged Object Segmentation

Abstract

Camouflaged objects are generally difficult to be detected in their natural environment even for human beings. In this paper, we propose a novel bio-inspired network, named the MirrorNet, that leverages both instance segmentation and mirror stream for the camouflaged object segmentation. Differently from existing networks for segmentation, our proposed network possesses two segmentation streams: the main stream and the mirror stream corresponding with the original image and its flipped image, respectively. The output from the mirror stream is then fused into the main stream's result for the final camouflage map to boost up the segmentation accuracy. Extensive experiments conducted on the public CAMO dataset demonstrate the effectiveness of our proposed network. Our proposed method achieves 89% in accuracy, outperforming the state-of-the-arts. Project Page: https://sites.google.com/view/ltnghia/research/camo

Accepted to IEEE Access

References in corpus (3)

• Fully Convolutional Networks for Semantic Segmentation
• Anabranch Network for Camouflaged Object Segmentation
• Salient Object Detection via Augmented Hypotheses

Cited by in corpus (7)

• Boundary-Guided Camouflaged Object Detection
• Feature Aggregation and Propagation Network for Camouflaged Object Detection
• Advances in Deep Concealed Scene Understanding
• ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
• Camouflaged Instance Segmentation In-The-Wild: Dataset, Method, and Benchmark Suite
• The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation
• Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation