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

翻译：即使在人类的自然环境中,也普遍很难探测到悬浮物体。 在本文中,我们提议建立一个名为镜像网的新型生物启发网络,它既能利用实例分割法,又能利用镜像流来进行伪装的物体分割法。与现有的分割法网络不同,我们提议的网络拥有两种分解流:主流和与原始图像及其翻动图像相对应的镜像流。然后,镜像流的输出被结合到主流的结果中,以便绘制最后的迷彩图,提高分解准确性。在公共 CAMO 数据集上进行的广泛实验显示了我们提议的网络的有效性。我们提议的方法在准确性上达到了89%,超过了艺术现状。项目页:https://sites.gogle.com/view/lthia/research/camo。项目页:https://sites.gle. com/view/ lthia/research/camo。