Efficient Segmentation: Learning Downsampling near Semantic Boundaries
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.
Cite
Text
Marin et al. "Efficient Segmentation: Learning Downsampling near Semantic Boundaries." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00222Markdown
[Marin et al. "Efficient Segmentation: Learning Downsampling near Semantic Boundaries." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/marin2019iccv-efficient/) doi:10.1109/ICCV.2019.00222BibTeX
@inproceedings{marin2019iccv-efficient,
title = {{Efficient Segmentation: Learning Downsampling near Semantic Boundaries}},
author = {Marin, Dmitrii and He, Zijian and Vajda, Peter and Chatterjee, Priyam and Tsai, Sam and Yang, Fei and Boykov, Yuri},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2019},
doi = {10.1109/ICCV.2019.00222},
url = {https://mlanthology.org/iccv/2019/marin2019iccv-efficient/}
}