Tilted cross-entropy (TCE)

Promoting fairness in semantic segmentation

Conference Paper (2021)
Author(s)

Attila Szabo (Shell Global Solutions International B.V.)

H Jamali-Rad (TU Delft - Pattern Recognition and Bioinformatics, Shell Global Solutions International B.V.)

Siva Datta Mannava (Shell Global Solutions International B.V.)

Research Group
Pattern Recognition and Bioinformatics
Copyright
© 2021 A.D. Szabó, H. Jamali-Rad, Siva Datta Mannava
DOI related publication
https://doi.org/10.1109/CVPRW53098.2021.00261
More Info
expand_more
Publication Year
2021
Language
English
Copyright
© 2021 A.D. Szabó, H. Jamali-Rad, Siva Datta Mannava
Research Group
Pattern Recognition and Bioinformatics
Pages (from-to)
2305-2310
ISBN (electronic)
9781665448994
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

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.

Files

License info not available