mlsanityData to 7 Oct 2026

FairViT: Fair Vision Transformer via Adaptive Masking

arXiv 2407.14799 ↗First posted 20 Jul 2024cs.CV cs.CYcited by 3

Not on the map. Why?

Abstract (arXiv)

Vision Transformer (ViT) has achieved excellent performance and demonstrated its promising potential in various computer vision tasks. The wide deployment of ViT in real-world tasks requires a thorough understanding of the societal impact of the model. However, most ViT-based works do not take fairness into account and it is unclear whether directly applying CNN-oriented debiased algorithm to ViT is feasible. Moreover, previous works typically sacrifice accuracy for fairness. Therefore, we aim to develop an algorithm that improves accuracy without sacrificing fairness. In this paper, we propose FairViT, a novel accurate and fair ViT framework. To this end, we introduce a novel distance loss and deploy adaptive fairness-aware masks on attention layers updating with model parameters. Experimental results show sys can achieve accuracy better than other alternatives, even with competitive computational efficiency. Furthermore, sys achieves appreciable fairness results.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 20 Jul 2024.

Builds on

27 of 36 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  8. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  9. 2020Quantifying Attention Flow in Transformerscited by 759
  10. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
  11. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  12. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
15 more
  1. 2021Understanding Robustness of Transformers for Image Classificationcited by 250
  2. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 206
  3. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  4. 2023Fair Diffusion: Instructing Text-to-Image Generation Models on Fairnesscited by 149
  5. 2021Multi-Scale High-Resolution Vision Transformer for Semantic Segmentationcited by 92
  6. 2020Toward Transformer-Based Object Detectioncited by 84
  7. 2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
  8. 2022A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributescited by 56
  9. 2022Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Modelscited by 47
  10. 2017Parallel Multi Channel Convolution using General Matrix Multiplicationcited by 30
  11. 2022ViT-CX: Causal Explanation of Vision Transformerscited by 27
  12. 2022Debiased Machine Learning without Sample-Splitting for Stable Estimatorscited by 13
  13. 2020README: REpresentation learning by fairness-Aware Disentangling MEthodcited by 10
  14. 2023Fairness-aware Vision Transformer via Debiased Self-Attentioncited by 6
  15. 2023Mitigating Bias in Visual Transformers via Targeted Alignmentcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Fair-MoE: Fairness-Oriented Mixture of Experts in Vision-Language Modelscited by 6
  2. 2026SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognitioncited by 1
  3. 2026FairNVT: Fair Classification via Noise Injection in Vision Transformerscited by 0