mlsanityData to 7 Oct 2026

Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective

arXiv 2111.03874 ↗First posted 6 Nov 2021cs.CV cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

Real-world data universally confronts a severe class-imbalance problem and exhibits a long-tailed distribution, i.e., most labels are associated with limited instances. The na"ive models supervised by such datasets would prefer dominant labels, encounter a serious generalization challenge and become poorly calibrated. We propose two novel methods from the prior perspective to alleviate this dilemma. First, we deduce a balance-oriented data augmentation named Uniform Mixup (UniMix) to promote mixup in long-tailed scenarios, which adopts advanced mixing factor and sampler in favor of the minority. Second, motivated by the Bayesian theory, we figure out the Bayes Bias (Bayias), an inherent bias caused by the inconsistency of prior, and compensate it as a modification on standard cross-entropy loss. We further prove that both the proposed methods ensure the classification calibration theoretically and empirically. Extensive experiments verify that our strategies contribute to a better-calibrated model, and their combination achieves state-of-the-art performance on CIFAR-LT, ImageNet-LT, and iNaturalist 2018.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 51 of its 70 references that are in the map. First posted on arXiv 6 Nov 2021.

Builds on

51 of 70 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2017Mask R-CNNcited by 7,259
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  8. 2017On Calibration of Modern Neural Networkscited by 4,860
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  11. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  12. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
38 more
  1. 2016End to End Learning for Self-Driving Carscited by 1,000
  2. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  3. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  4. 2017Focal Loss for Dense Object Detectioncited by 749
  5. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  6. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  7. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  8. 2016Learning to learn by gradient descent by gradient descentcited by 616
  9. 2020Long-tail learning via logit adjustmentcited by 605
  10. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
  11. 2019Measuring Calibration in Deep Learningcited by 443
  12. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  13. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  14. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  15. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  16. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  17. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  18. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 250
  19. 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
  20. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  21. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  22. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 208
  23. 2020How Does Mixup Help With Robustness and Generalization?cited by 193
  24. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  25. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  26. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  27. 2020Remix: Rebalanced Mixupcited by 144
  28. 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
  29. 2020Feature Space Augmentation for Long-Tailed Datacited by 136
  30. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  31. 2015Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networkscited by 115
  32. 2018Gradient Harmonized Single-stage Detectorcited by 114
  33. 2018Deep Imbalanced Learning for Face Recognition and Attribute Predictioncited by 90
  34. 2017The Devil is in the Tails: Fine-grained Classification in the Wildcited by 89
  35. 2019Striking the Right Balance with Uncertaintycited by 79
  36. 2020Identifying and Compensating for Feature Deviation in Imbalanced Deep Learningcited by 76
  37. 2019Generative Adversarial Minority Oversamplingcited by 72
  38. 2019Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Datacited by 33

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 15; 2024: 11; 2025: 5; 2026: 2.

39 papers.

Sort:

By area:

  1. 2022RankSim: Ranking Similarity Regularization for Deep Imbalanced Regressioncited by 52
  2. 2022Learning Imbalanced Data with Vision Transformerscited by 34
  3. 2024A Systematic Review on Long-Tailed Learningcited by 27
  4. 2023A Unified Perspective for Loss-Oriented Imbalanced Learning via Localizationcited by 24
  5. 2024HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shiftscited by 22
  6. 2022Balanced Product of Calibrated Experts for Long-Tailed Recognitioncited by 20
  7. 2023RankMixup: Ranking-Based Mixup Training for Network Calibrationcited by 19
  8. 2024A Survey on Mixup Augmentations and Beyondcited by 18
  9. 2023Calibrating Multimodal Learningcited by 17
  10. 2023NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognitioncited by 14
  11. 2023Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraintscited by 13
  12. 2024Revisiting Adversarial Training under Long-Tailed Distributionscited by 13
27 more
  1. 2023Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distributioncited by 12
  2. 2024Geometric Prior Guided Feature Representation Learning for Long-Tailed Classificationcited by 10
  3. 2024On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Modelscited by 10
  4. 2023Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifoldscited by 9
  5. 2022Taming the Long Tail of Deep Probabilistic Forecastingcited by 7
  6. 2023Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibrationcited by 7
  7. 2024BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learningcited by 6
  8. 2024Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentationcited by 6
  9. 2024Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Taskscited by 6
  10. 2025Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Modelcited by 6
  11. 2022Compound Batch Normalization for Long-tailed Image Classificationcited by 5
  12. 2023Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metricscited by 5
  13. 2023Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learningcited by 5
  14. 2023Delving Deep into Simplicity Bias for Long-Tailed Image Recognitioncited by 3
  15. 2023Overcoming Overconfidence for Active Learningcited by 3
  16. 2024DiffuLT: How to Make Diffusion Model Useful for Long-tail Recognitioncited by 3
  17. 2022Data Augmentation by Selecting Mixed Classes Considering Distance Between Classescited by 2
  18. 2023Rethink Long-tailed Recognition with Vision Transformerscited by 2
  19. 2025Beyond One-Hot Labels: Semantic Mixing for Model Calibrationcited by 2
  20. 2023Ranking Regularization for Critical Rare Classes: Minimizing False Positives at a High True Positive Ratecited by 1
  21. 2023Towards Effective Collaborative Learning in Long-Tailed Recognitioncited by 1
  22. 2025Open Set Label Shift with Test Time Out-of-Distribution Referencecited by 1
  23. 2024Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognitioncited by 0
  24. 2025PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusioncited by 0
  25. 2025LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarioscited by 0
  26. 2026Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignmentcited by 0
  27. 2026Label Shift Aware Adaptation for Online Zero-shot Learning with Contrastive Language-Image Pre-Training (CLIP)cited by 0