Edge-guided Hierarchically Nested Network for Real-time Semantic Segmentation

Yuqi Li, Sei Ichiro Kamata, Haoran Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Semantic segmentation requires both large region context information and rich spatial information. The former can be achieved by a deep-enough network structure. However, most spatial information lost in repeated down-sample operation in deep Convolutional Neural Networks cannot be easily recovered. In this paper, we propose a novel edge-guided hierarchically nested network to improve both speed and accuracy of real-time semantic segmentation. We introduce Edge Guidance Unit which aims to guide the decoder network to exploit high-resolution clues, recover and refine spatial information with low additional computational cost. We also introduce a well-designed Fusion Block to combine different resolution features along with edge guidance. In experiments we demonstrate that our network stabilizes the small object region while achieving a result of 72.7% mean IoU at 40 FPS on CityScapes test dataset.

Original languageEnglish
Title of host publicationProceedings of the 2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages296-301
Number of pages6
ISBN (Electronic)9781728133775
DOIs
Publication statusPublished - 2019 Sep
Event2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019 - Kuala Lumpur, Malaysia
Duration: 2019 Sep 172019 Sep 19

Publication series

NameProceedings of the 2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019

Conference

Conference2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019
CountryMalaysia
CityKuala Lumpur
Period19/9/1719/9/19

Keywords

  • edge guidance unit
  • hierarchically nested network
  • real-time semantic segmentation

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Health Informatics
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Edge-guided Hierarchically Nested Network for Real-time Semantic Segmentation'. Together they form a unique fingerprint.

  • Cite this

    Li, Y., Kamata, S. I., & Liu, H. (2019). Edge-guided Hierarchically Nested Network for Real-time Semantic Segmentation. In Proceedings of the 2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019 (pp. 296-301). [8977788] (Proceedings of the 2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSIPA45851.2019.8977788