SOTAVerified

Learning a Discriminative Feature Network for Semantic Segmentation

2018-04-25CVPR 2018Code Available0· sign in to hype

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

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
Cityscapes testSmooth Network with Channel Attention BlockMean IoU (class)80.3Unverified
Cityscapes testDFN (ResNet-101)Mean IoU (class)79.3Unverified
PASCAL VOC 2012 testSmooth Network with Channel Attention BlockMean IoU86.2Unverified
PASCAL VOC 2012 testDFN (ResNet-101)Mean IoU82.7Unverified
PASCAL VOC 2012 valDFN (ResNet-101)mIoU80.6Unverified

Reproductions