mlsanityData to 7 Oct 2026

REPAIR: Removing Representation Bias by Dataset Resampling

arXiv 1904.07911 ↗First posted 16 Apr 2019cs.CVcited by 157

Not on the map. Why?

Abstract (arXiv)

Modern machine learning datasets can have biases for certain representations that are leveraged by algorithms to achieve high performance without learning to solve the underlying task. This problem is referred to as "representation bias". The question of how to reduce the representation biases of a dataset is investigated and a new dataset REPresentAtion bIas Removal (REPAIR) procedure is proposed. This formulates bias minimization as an optimization problem, seeking a weight distribution that penalizes examples easy for a classifier built on a given feature representation. Bias reduction is then equated to maximizing the ratio between the classification loss on the reweighted dataset and the uncertainty of the ground-truth class labels. This is a minimax problem that REPAIR solves by alternatingly updating classifier parameters and dataset resampling weights, using stochastic gradient descent. An experimental set-up is also introduced to measure the bias of any dataset for a given representation, and the impact of this bias on the performance of recognition models. Experiments with synthetic and action recognition data show that dataset REPAIR can significantly reduce representation bias, and lead to improved generalization of models trained on REPAIRed datasets. The tools used for characterizing representation bias, and the proposed dataset REPAIR algorithm, are available at https://github.com/JerryYLi/Dataset-REPAIR/.

Key facts. Cited by 157 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 53; 2023: 30; 2024: 23; 2025: 14; 2026: 7.

157 papers.

Sort:

By area:

  1. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  2. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  3. 2021AGQA: A Benchmark for Compositional Spatio-Temporal Reasoningcited by 120
  4. 2021Learning Debiased Representation via Disentangled Feature Augmentationcited by 116
  5. 2022Temporal Action Segmentation: An Analysis of Modern Techniquescited by 85
  6. 2022Debiasing Graph Neural Networks via Learning Disentangled Causal Substructurecited by 83
  7. 2021FINE Samples for Learning with Noisy Labelscited by 82
  8. 2021Causal Attention for Unbiased Visual Recognitioncited by 80
  9. 2021BiaSwap: Removing dataset bias with bias-tailored swapping augmentationcited by 70
  10. 2023Fast Model Debias with Machine Unlearningcited by 70
  11. 2021Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answeringcited by 62
  12. 2022Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifierscited by 53
38 more
  1. 2022Learning Debiased Classifier with Biased Committeecited by 51
  2. 2022Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Modelscited by 47
  3. 2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
  4. 2021On Semantic Similarity in Video Retrievalcited by 45
  5. 2021Unsupervised Learning of Debiased Representations with Pseudo-Attributescited by 44
  6. 2022Representation Bias in Data: A Survey on Identification and Resolution Techniquescited by 37
  7. 2022Going Beyond XAI: A Systematic Survey for Explanation-Guided Learningcited by 35
  8. 2022Avoiding spurious correlations via logit correctioncited by 32
  9. 2022FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classificationcited by 30
  10. 2022Bias Mimicking: A Simple Sampling Approach for Bias Mitigationcited by 30
  11. 2022SelecMix: Debiased Learning by Contradicting-pair Samplingcited by 29
  12. 2023Overcoming Simplicity Bias in Deep Networks using a Feature Sievecited by 29
  13. 2022Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lenscited by 28
  14. 2021Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalizationcited by 27
  15. 2021A Stochastic Optimization Framework for Fair Risk Minimizationcited by 26
  16. 2022Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foregroundcited by 26
  17. 2023HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actionscited by 25
  18. 2022A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Informationcited by 24
  19. 2022Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustnesscited by 23
  20. 2021Learning Representational Invariances for Data-Efficient Action Recognitioncited by 22
  21. 2022Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Surveycited by 22
  22. 2024Understanding Video Transformers via Universal Concept Discoverycited by 22
  23. 2022Mitigating Dataset Bias by Using Per-sample Gradientcited by 21
  24. 2022On Modality Bias Recognition and Reductioncited by 20
  25. 2025Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Videocited by 20
  26. 2022Revisiting the Importance of Amplifying Bias for Debiasingcited by 19
  27. 2022Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentationcited by 18
  28. 2022Unbiased Directed Object Attention Graph for Object Navigationcited by 17
  29. 2021Learning Debiased and Disentangled Representations for Semantic Segmentationcited by 16
  30. 2022Training Debiased Subnetworks with Contrastive Weight Pruningcited by 16
  31. 2024The Pitfalls of Memorization: When Memorization Hurts Generalizationcited by 16
  32. 2021Robust Semantic Interpretability: Revisiting Concept Activation Vectorscited by 15
  33. 2021Can Active Learning Preemptively Mitigate Fairness Issues?cited by 15
  34. 2022Information-Theoretic Bias Reduction via Causal View of Spurious Correlationcited by 15
  35. 2023ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videoscited by 15
  36. 2021Are Bias Mitigation Techniques for Deep Learning Effective?cited by 14
  37. 2022Pseudo Bias-Balanced Learning for Debiased Chest X-ray Classificationcited by 14
  38. 2023Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issuescited by 12

50 most cited of 157 All 157 (JSON)