Method Details

Details for method 'DFN'

name	DFN
challenge	pixel-level semantic labeling
details	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.
publication	Learning a Discriminative Feature Network for Semantic Segmentation Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang arxiv
project page / code
used Cityscapes data	fine annotations, coarse annotations
used external data	ImageNet
runtime	n/a
subsampling	no
submission date	December, 2017
previous submissions