Method Details

Details for method 'DecoupleSegNet'

name	DecoupleSegNet
challenge	pixel-level semantic labeling
details	In this paper, We propose a new paradigm for semantic segmentation. Our insight is that appealing performance of semantic segmentation re- quires explicitly modeling the object body and edge, which correspond to the high and low frequency of the image. To do so, we first warp the image feature by learning a flow field to make the object part more consistent. The resulting body feature and the residual edge feature are further optimized under decoupled supervision by explicitly sampling dif- ferent parts (body or edge) pixels. The code and models have been released.
publication	Improving Semantic Segmentation via Decoupled Body and Edge Supervision Xiangtai Li, Xia Li, Li Zhang, Guangliang Cheng, Jianping Shi, Zhouchen Lin, Shaohua Tan, and Yunhai Tong ECCV-2020 https://arxiv.org/abs/2007.10035
project page / code	https://github.com/lxtGH/DecoupleSegNets
used Cityscapes data	fine annotations
used external data	ImageNet
runtime	n/a
subsampling	no
submission date	January, 2020
previous submissions