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 setting 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 efficiently improve the low-performing classes of Cityscapes and ADE20k datasets trained with multi-class cross-entropy (MCCE), and also results in improved overall fairness.

翻译：由于最近引入的倾斜型机构风险管理(TERM),我们建议倾斜性跨热带(TCE)损失,使之适应语义分解环境,以尽量减少目标类别之间的业绩差异,促进公平。 通过定量和定性绩效分析,我们证明拟议的用于语义分解的Stochatic TCE能够有效地改善低效城市风景类别和接受多级跨热带(MCCE)培训的ADE20k数据集,并导致总体公平性提高。