Learning a Discriminative Feature Network for Semantic Segmentation

Changqian Yu; Jingbo Wang; Chao Peng; Changxin Gao; Gang Yu; Nong Sang

CVPR 2018poster987 citations

Learning a Discriminative Feature Network for Semantic Segmentation

Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang

Abstract

Most existing methods of semantic segmentation still suffer from two aspects of challenges: intra-class inconsistency and inter-class indistinction. To tackle these two problems, we propose a Discriminative Feature Network (DFN), which contains two sub-networks: Smooth Network and Border Network. Specifically, to handle the intra-class inconsistency problem, we specially design a Smooth Network with Channel Attention Block and global average pooling to select the more discriminative features. Furthermore, we propose a Border Network to make the bilateral features of boundary distinguishable with deep semantic boundary supervision. Based on our proposed DFN, we achieve state-of-the-art performance 86.2% mean IOU on PASCAL VOC 2012 and 80.3% mean IOU on Cityscapes dataset.

BibTeX

@inproceedings{cvpr2018_learningadiscrim,
  title = {Learning a Discriminative Feature Network for Semantic Segmentation},
  author = {Changqian Yu and Jingbo Wang and Chao Peng and Changxin Gao and Gang Yu and Nong Sang},
  booktitle = {CVPR 2018},
  year = {2018}
}