论文标题
MirrorNet：生物启发的伪装物体分割
MirrorNet: Bio-Inspired Camouflaged Object Segmentation
论文作者
论文摘要
即使对于人类，在自然环境中通常很难在其自然环境中检测到伪装的物体。在本文中，我们提出了一个新型的生物启发的网络，名为Mirrornet，该网络利用了伪装的对象分割来利用实例分割和镜像流。与现有网络进行分割不同，我们提出的网络具有两个分割流：主流和镜像流分别与原始图像及其翻转图像相对应。然后将来自镜像流的输出融合到主流的结果中，以提高分割精度。在公共迷彩数据集上进行的广泛实验证明了我们提出的网络的有效性。我们提出的方法的准确性达到了89％，表现优于最先进的方法。 项目页面：https：//sites.google.com/view/ltnghia/research/camo
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
