@inproceedings{5fa21f2890b04bbab7e956f67c6b1933,
title = "Tilted cross-entropy (TCE): Promoting fairness in semantic segmentation",
abstract = "Traditional empirical risk minimization (ERM) for semantic segmentation can disproportionately advantage or disadvantage certain target classes in favor of an (unfair but) improved overall performance. Inspired by the recently introduced tilted ERM (TERM), we propose tilted cross-entropy (TCE) loss and adapt it to the semantic segmentation set-ting to minimize performance disparity among target classes and promote fairness. Through quantitative and qualitative performance analyses, we demonstrate that the proposed Stochastic TCE for semantic segmentation can offer improved overall fairness by efficiently minimizing the performance disparity among the target classes of Cityscapes.",
author = "Attila Szabo and Hadi Jamali-Rad and Mannava, {Siva Datta}",
year = "2021",
doi = "10.1109/CVPRW53098.2021.00261",
language = "English",
series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",
publisher = "IEEE",
pages = "2305--2310",
booktitle = "Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021",
address = "United States",
note = "2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 ; Conference date: 19-06-2021 Through 25-06-2021",
}