# Learning a Discriminative Feature Network for Semantic Segmentation

Source: [Learning a Discriminative Feature Network for Semantic Segmentation](<https://www.sota2.com/research/paper/68fa64431e209131cea0397d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T02:57:19.237Z

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

Published: 2018-04-25T03:49:30.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Semantic Segmentation on Cityscapes fine-only (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-fine-only-test.md>): Semantic segmentation; Cityscapes fine-only (test); mIoU: 79.3.

- [Semantic Segmentation on Cityscapes v1.1 (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-v1-1-test.md>): Semantic segmentation; Cityscapes v1.1 (test); mIoU: 79.3.

- [Semantic Segmentation on Pascal VOC (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-voc-test.md>): Semantic segmentation; Pascal VOC (test); mIoU: 86.2.

- [Semantic Segmentation on MFNet daytime (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-mfnet-daytime-test.md>): Semantic segmentation; MFNet daytime (test); mIoU: 38.

- [Semantic Segmentation on PASCAL VOC 2012 (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-voc-2012-test.md>): Semantic segmentation; PASCAL VOC 2012 (test); mIoU: 86.2.

- [Semantic Segmentation on MFNet nighttime (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-mfnet-nighttime-test.md>): Semantic segmentation; MFNet nighttime (test); mIoU: 42.3.

- [Semantic Segmentation on PASCAL VOC 2012 (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-voc-2012-val.md>): Semantic segmentation; PASCAL VOC 2012 (val); Mean IoU: 80.46.

- [Semantic Segmentation on Cityscapes (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-test.md>): Semantic segmentation; Cityscapes (test); mIoU: 80.3.

- [Semantic Segmentation on CamVid (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-camvid-test.md>): Semantic segmentation; CamVid (test); mIoU: 60.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1804.09337>)

[PDF](<https://arxiv.org/pdf/1804.09337.pdf>)