mlsanityData to 14 Oct 2026

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

arXiv 2103.14051 ↗First posted 25 Mar 2021cs.CV cs.AI cs.LGcited by 12

Not on the map. Why?

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.

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

24 of 34 references.

References · 24

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  5. 2016Pyramid Scene Parsing Networkcited by 2,479
  6. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  7. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  8. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  9. 2018Panoptic Segmentationcited by 802
  10. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  11. 2015Holistically-Nested Edge Detectioncited by 592
  12. 2019Agnostic Federated Learningcited by 456
12 more
  1. 2019Fair Resource Allocation in Federated Learningcited by 394
  2. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 364
  3. 2018Context Encoding for Semantic Segmentationcited by 290
  4. 2020A survey of loss functions for semantic segmentationcited by 217
  5. 2016Variance-based regularization with convex objectivescited by 155
  6. 2019Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networkscited by 116
  7. 2020Tilted Empirical Risk Minimizationcited by 106
  8. 2018Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learningcited by 81
  9. 2018ExFuse: Enhancing Feature Fusion for Semantic Segmentationcited by 42
  10. 20183D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizescited by 42
  11. 2018Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networkscited by 12
  12. 2017Conditional Adversarial Network for Semantic Segmentation of Brain Tumorcited by 10

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 3; 2023: 3; 2024: 4.

12 papers.

  1. 2021On Tilted Losses in Machine Learning: Theory and Applicationscited by 43
  2. 2023FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understandingcited by 27
  3. 2023Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environmentscited by 16
  4. 2023FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understandingcited by 13
  5. 2022How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shiftscited by 11
  6. 2022Segmenting across places: The need for fair transfer learning with satellite imagerycited by 6
  7. 2024Tilted Sharpness-Aware Minimizationcited by 6
  8. 2024Generalization and Robustness of the Tilted Empirical Riskcited by 4
  9. 2021SemSegLoss: A python package of loss functions for semantic segmentationcited by 3
  10. 2022Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite Imagerycited by 1
  11. 2024Efficient k-means with Individual Fairness via Exponential Tiltingcited by 0
  12. 2024Understanding and Reducing the Class-Dependent Effects of Data Augmentation with A Two-Player Game Approachcited by 0