Tilted cross-entropy (TCE)

Promoting fairness in semantic segmentation

Conference paper (2021)

Authors

Attila Szabo Shell Global Solutions International B.V.
H. Jamali-Rad Pattern Recognition and Bioinformatics - EEMCS , Shell Global Solutions International B.V.
Siva Datta Mannava Shell Global Solutions International B.V.
Research Group
Pattern Recognition and Bioinformatics (EEMCS) (TU Delft)
Copyright: © 2021 A.D. Szabó, H. Jamali-Rad, Siva Datta Mannava
DOI: https://doi.org/10.1109/CVPRW53098.2021.00261
More Info
expand_more

Published Date

2021

Language

English

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.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Intelligent Systems

Research Group

Pattern Recognition and Bioinformatics

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.