Efficient Light Deep Network for Street Scene Parsing

Zhe Hui Wang, Sanyuan Zhao, Jianbing Shen, Zhengchao Lei

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

The semantic segmentation is a dense pixel label pre-diction task, which takes quite a lot of resources and computation cost in most of the time. In our approach, we pay attention to balance the speed and better performance which outperforms the state of the art in speed and accuracy for real-time performance. We come up with the idea of new efficient deep backbone that can extract more semantic details, reduce the computation cost and be easy to deploy at the same time. We call our new backbone as Cascaded Mobile Network, which is proved to be very useful. Our proposed model achieves 72.1 mIOU on the CityScapes val, and 69.5 on CamVid. We achieve good balance between speed and accuracy.

源语言英语
主期刊名2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020
出版商Institute of Electrical and Electronics Engineers Inc.
42-45
页数4
ISBN(电子版)9781728180670
DOI
出版状态已出版 - 1 12月 2020
活动2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020 - Virtual, Macau, 中国
期限: 1 12月 20204 12月 2020

出版系列

姓名2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020

会议

会议2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020
国家/地区中国
Virtual, Macau
时期1/12/204/12/20

指纹

探究 'Efficient Light Deep Network for Street Scene Parsing' 的科研主题。它们共同构成独一无二的指纹。

引用此

Wang, Z. H., Zhao, S., Shen, J., & Lei, Z. (2020). Efficient Light Deep Network for Street Scene Parsing. 在 2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020 (页码 42-45). 文章 9301795 (2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VCIP49819.2020.9301795