论文标题
深蛇实例分段
Deep Snake for Real-Time Instance Segmentation
论文作者
论文摘要
本文介绍了一种基于轮廓的新方法，名为Deep Snake，用于实时实例分割。与一些直接从图像从对象边界点重新回归对象边界点的坐标的方法不同，Deep Snake使用神经网络迭代变形初始轮廓以匹配对象边界，该轮廓与基于学习的方法实现了蛇算法的经典思想。对于轮廓上的结构化特征学习，我们建议在深蛇中使用圆形卷积，这更好地利用了与通用图卷积相比的轮廓的循环图形结构。基于Deep Snake，我们开发了一个两个阶段的管道，例如分割：初始轮廓建议和轮廓变形，可以处理对象定位中的错误。实验表明，所提出的方法可以在城市景观，亲戚，SBD和可可数据集上实现竞争性能，同时在1080ti GPU上的512美元$ 512 $ 512图像的速度为32.3 fps的实时应用程序有效。该代码可在https://github.com/zju3dv/snake/上找到。
This paper introduces a novel contour-based approach named deep snake for real-time instance segmentation. Unlike some recent methods that directly regress the coordinates of the object boundary points from an image, deep snake uses a neural network to iteratively deform an initial contour to match the object boundary, which implements the classic idea of snake algorithms with a learning-based approach. For structured feature learning on the contour, we propose to use circular convolution in deep snake, which better exploits the cycle-graph structure of a contour compared against generic graph convolution. Based on deep snake, we develop a two-stage pipeline for instance segmentation: initial contour proposal and contour deformation, which can handle errors in object localization. Experiments show that the proposed approach achieves competitive performances on the Cityscapes, KINS, SBD and COCO datasets while being efficient for real-time applications with a speed of 32.3 fps for 512$\times$512 images on a 1080Ti GPU. The code is available at https://github.com/zju3dv/snake/.
