# Tilted Cross Entropy (TCE): Promoting Fairness in Semantic Segmentation

arXiv: https://arxiv.org/abs/2103.14051 · HTML: https://mlsanity.com/paper/2103.14051/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 25 Mar 2021.

## Builds on (most cited first, 24 of 24)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [Context Encoding for Semantic Segmentation](https://mlsanity.com/paper/1803.08904/) (2018)
- [A survey of loss functions for semantic segmentation](https://mlsanity.com/paper/2006.14822/) (2020)
- [Variance-based regularization with convex objectives](https://mlsanity.com/paper/1610.02581/) (2016)
- [Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks](https://mlsanity.com/paper/1904.10030/) (2019)
- [Tilted Empirical Risk Minimization](https://mlsanity.com/paper/2007.01162/) (2020)
- [Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning](https://mlsanity.com/paper/1803.01207/) (2018)
- [ExFuse: Enhancing Feature Fusion for Semantic Segmentation](https://mlsanity.com/paper/1804.03821/) (2018)
- [3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes](https://mlsanity.com/paper/1809.00076/) (2018)
- [Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networks](https://mlsanity.com/paper/1802.01445/) (2018)
- [Conditional Adversarial Network for Semantic Segmentation of Brain Tumor](https://mlsanity.com/paper/1708.05227/) (2017)

## Built on by (most cited first, 12 of 12)

- [On Tilted Losses in Machine Learning: Theory and Applications](https://mlsanity.com/paper/2109.06141/) (2021)
- [FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding](https://mlsanity.com/paper/2304.02135/) (2023)
- [Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments](https://mlsanity.com/paper/2305.15700/) (2023)
- [FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding](https://mlsanity.com/paper/2311.15965/) (2023)
- [How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts](https://mlsanity.com/paper/2207.01168/) (2022)
- [Segmenting across places: The need for fair transfer learning with satellite imagery](https://mlsanity.com/paper/2204.04358/) (2022)
- [Tilted Sharpness-Aware Minimization](https://mlsanity.com/paper/2410.22656/) (2024)
- [Generalization and Robustness of the Tilted Empirical Risk](https://mlsanity.com/paper/2409.19431/) (2024)
- [SemSegLoss: A python package of loss functions for semantic segmentation](https://mlsanity.com/paper/2106.05844/) (2021)
- [Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite Imagery](https://mlsanity.com/paper/2211.08672/) (2022)
- [Efficient k-means with Individual Fairness via Exponential Tilting](https://mlsanity.com/paper/2406.16557/) (2024)
- [Understanding and Reducing the Class-Dependent Effects of Data Augmentation with A Two-Player Game Approach](https://mlsanity.com/paper/2407.03146/) (2024)

## Abstract (arXiv)

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.