Method Details

Details for method 'DRN_CRL_Coarse'

name	DRN_CRL_Coarse
challenge	pixel-level semantic labeling
details	Semantic image segmentation, which aims at assigning pixel-wise category, is one of challenging image understanding problems. Global context plays an important role on local pixel-wise category assignment. To make the best of global context, in this paper, we propose dense relation network (DRN) and context-restricted loss (CRL) to aggregate global and local information. DRN uses Recurrent Neural Network (RNN) with different skip lengths in spatial directions to get context-aware representations while CRL helps aggregate them to learn consistency. Compared with previous methods, our proposed method takes full advantage of hierarchical contextual representations to produce high-quality results. Extensive experiments demonstrate that our methods achieves significant state-of-the-art performances on Cityscapes and Pascal Context benchmarks, with mean-IoU of 82.8\% and 49.0\% respectively.
publication	Dense Relation Network: Learning Consistent and Context-Aware Representation For Semantic Image Segmentation Yueqing Zhuang ICIP
project page / code	https://github.com/zhuangyqin/DRN.git
used Cityscapes data	fine annotations, coarse annotations
used external data	ImageNet
runtime	n/a
subsampling	no
submission date	February, 2018
previous submissions