Deep Snake for Real-Time Instance Segmentation

CVPR 2020 Sida PengWen JiangHuaijin PiXiuli LiHujun BaoXiaowei Zhou

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... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Semantic Contour Prediction Sbd val Deep snake AP50 62.1 # 1
AP70 48.3 # 1
APvol 54.4 # 1

Methods used in the Paper