Optimizing Expected Intersection-over-Union with Candidate-Constrained CRFs
Abstract
We study the question of how to make loss-aware predictions in image segmentation settings where the evaluation function is the Intersection-over-Union (IoU) measure that is used widely in evaluating image segmentation systems. Currently, there are two dominant approaches: the first approximates the Expected-IoU (EIoU) score as Expected-Intersection-over-Expected-Union (EIoEU); and the second approach is to compute exact EIoU but only over a small set of high-quality candidate solutions. We begin by asking which approach we should favor for two typical image segmentation tasks. Studying this question leads to two new methods that draw ideas from both existing approaches. Our new methods use the EIoEU approximation paired with high quality candidate solutions. Experimentally we show that our new approaches lead to improved performance on both image segmentation tasks.
Cite
Text
Ahmed et al. "Optimizing Expected Intersection-over-Union with Candidate-Constrained CRFs." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.215Markdown
[Ahmed et al. "Optimizing Expected Intersection-over-Union with Candidate-Constrained CRFs." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/ahmed2015iccv-optimizing/) doi:10.1109/ICCV.2015.215BibTeX
@inproceedings{ahmed2015iccv-optimizing,
title = {{Optimizing Expected Intersection-over-Union with Candidate-Constrained CRFs}},
author = {Ahmed, Faruk and Tarlow, Dany and Batra, Dhruv},
booktitle = {International Conference on Computer Vision},
year = {2015},
doi = {10.1109/ICCV.2015.215},
url = {https://mlanthology.org/iccv/2015/ahmed2015iccv-optimizing/}
}