Efficient Segmentation: Learning Downsampling Near Semantic Boundaries

Dmitrii Marin, Zijian He, Peter Vajda, Priyam Chatterjee, Sam Tsai, Fei Yang, Yuri Boykov; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 2131-2141

Abstract


Many automated processes such as auto-piloting rely on a good semantic segmentation as a critical component. To speed up performance, it is common to downsample the input frame. However, this comes at the cost of missed small objects and reduced accuracy at semantic boundaries. To address this problem, we propose a new content-adaptive downsampling technique that learns to favor sampling locations near semantic boundaries of target classes. Cost-performance analysis shows that our method consistently outperforms the uniform sampling improving balance between accuracy and computational efficiency. Our adaptive sampling gives segmentation with better quality of boundaries and more reliable support for smaller-size objects.

Related Material


[pdf]
[bibtex]
@InProceedings{Marin_2019_ICCV,
author = {Marin, Dmitrii and He, Zijian and Vajda, Peter and Chatterjee, Priyam and Tsai, Sam and Yang, Fei and Boykov, Yuri},
title = {Efficient Segmentation: Learning Downsampling Near Semantic Boundaries},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}