Command Palette
Search for a command to run...
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.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| semantic-segmentation-on-cityscapes | DFN (ResNet-101) | Mean IoU (class): 79.3% |
| semantic-segmentation-on-cityscapes | Smooth Network with Channel Attention Block | Mean IoU (class): 80.3% |
| semantic-segmentation-on-pascal-voc-2012 | Smooth Network with Channel Attention Block | Mean IoU: 86.2% |
| semantic-segmentation-on-pascal-voc-2012 | DFN (ResNet-101) | Mean IoU: 82.7% |
| semantic-segmentation-on-pascal-voc-2012-val | DFN (ResNet-101) | mIoU: 80.60% |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.