Deep Snake for Real-Time Instance Segmentation
This addresses the problem of efficient instance segmentation for applications requiring real-time processing, such as autonomous driving, though it is an incremental improvement by integrating learning into classic snake algorithms.
The paper tackles real-time instance segmentation by introducing deep snake, a contour-based method that iteratively deforms an initial contour to match object boundaries, achieving competitive performance on datasets like Cityscapes and COCO with a speed of 32.3 fps.
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/.