# MirrorNet: Bio-Inspired Camouflaged Object Segmentation

arXiv: https://arxiv.org/abs/2007.12881 · HTML: https://mlsanity.com/paper/2007.12881/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2020.

## Built on by (most cited first, 11 of 11)

- [Simultaneously Localize, Segment and Rank the Camouflaged Objects](https://mlsanity.com/paper/2103.04011/) (2021)
- [Camouflaged Object Segmentation with Distraction Mining](https://mlsanity.com/paper/2104.10475/) (2021)
- [Mutual Graph Learning for Camouflaged Object Detection](https://mlsanity.com/paper/2104.02613/) (2021)
- [Context-aware Cross-level Fusion Network for Camouflaged Object Detection](https://mlsanity.com/paper/2105.12555/) (2021)
- [Boundary-Aware Segmentation Network for Mobile and Web Applications](https://mlsanity.com/paper/2101.04704/) (2021)
- [Feature Aggregation and Propagation Network for Camouflaged Object Detection](https://mlsanity.com/paper/2212.00990/) (2022)
- [Camouflaged Object Detection via Context-aware Cross-level Fusion](https://mlsanity.com/paper/2207.13362/) (2022)
- [Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels](https://mlsanity.com/paper/2110.15606/) (2021)
- [Exploring Depth Contribution for Camouflaged Object Detection](https://mlsanity.com/paper/2106.13217/) (2021)
- [Confidence-Aware Learning for Camouflaged Object Detection](https://mlsanity.com/paper/2106.11641/) (2021)
- [Towards Accurate Camouflaged Object Detection with Mixture Convolution and Interactive Fusion](https://mlsanity.com/paper/2101.05687/) (2021)

## Abstract (arXiv)

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