Data to 7 Oct 2026

Improving Calibration for Long-Tailed Recognition

arXiv 2104.00466 ↗First posted 1 Apr 2021cs.CVcited by 212

Not on the map. Why?

Abstract (arXiv)

Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to improve performance. But there is still the vital issue of miscalibration. To address it, we design two methods to improve calibration and performance in such scenarios. Motivated by the fact that predicted probability distributions of classes are highly related to the numbers of class instances, we propose label-aware smoothing to deal with different degrees of over-confidence for classes and improve classifier learning. For dataset bias between these two stages due to different samplers, we further propose shifted batch normalization in the decoupling framework. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets, including CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, Places-LT, and iNaturalist 2018. Code will be available at https://github.com/Jia-Research-Lab/MiSLAS.

Key facts. Cited by 212 papers in the map (data through 7 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 1 Apr 2021.

Builds on

27 of 40 references.

References · 27

2015Deep Residual Learning for Image Recognitioncited by 51,809
2014Microsoft COCO: Common Objects in Contextcited by 17,498
2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
2017On Calibration of Modern Neural Networkscited by 4,860
2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239

15 more

2016End to End Learning for Self-Driving Carscited by 1,000
2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
2019When Does Label Smoothing Help?cited by 985
2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
2020Calibrating Deep Neural Networks using Focal Losscited by 353
2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
2018What is the Effect of Importance Weighting in Deep Learning?cited by 250
2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
2020Remix: Rebalanced Mixupcited by 144
2015Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networkscited by 115
2016Range Loss for Deep Face Recognition with Long-tailcited by 111

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 42; 2023: 56; 2024: 54; 2025: 31; 2026: 18.

212 papers.

Sort:

By area:

2021Deep Long-Tailed Learning: A Surveycited by 416
2021Parametric Contrastive Learningcited by 217
2021The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classificationcited by 100
2022Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?cited by 100
2021Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognitioncited by 95
2022A Survey on Long-Tailed Visual Recognitioncited by 75
2023Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustmentcited by 75
2022LPT: Long-tailed Prompt Tuning for Image Classificationcited by 69
2022Nested Collaborative Learning for Long-Tailed Visual Recognitioncited by 63
2023Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurtscited by 58
2022RankSim: Ranking Similarity Regularization for Deep Imbalanced Regressioncited by 52
2023Understanding Imbalanced Semantic Segmentation Through Neural Collapsecited by 46

38 more

2022Generalized Parametric Contrastive Learningcited by 45
2022Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learningcited by 43
2023Rethinking Confidence Calibration for Failure Predictioncited by 43
2021Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspectivecited by 39
2022Long-Tailed Class Incremental Learningcited by 36
2023How Re-sampling Helps for Long-Tail Learning?cited by 36
2021Robust Long-Tailed Learning under Label Noisecited by 35
2022Learning Imbalanced Data with Vision Transformerscited by 34
2023Fill-Up: Balancing Long-Tailed Data with Generative Modelscited by 34
2023Feedback-guided Data Synthesis for Imbalanced Classificationcited by 33
2024LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Contentcited by 33
2022BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learningcited by 29
2022Escaping Saddle Points for Effective Generalization on Class-Imbalanced Datacited by 28
2023Inducing Neural Collapse in Deep Long-tailed Learningcited by 28
2024A Systematic Review on Long-Tailed Learningcited by 27
2023Subclass-balancing Contrastive Learning for Long-tailed Recognitioncited by 26
2022Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasetscited by 25
2022Constructing Balance from Imbalance for Long-tailed Image Recognitioncited by 25
2023Beyond Confidence: Reliable Models Should Also Consider Atypicalitycited by 25
2023A Unified Perspective for Loss-Oriented Imbalanced Learning via Localizationcited by 24
2023Use Your Head: Improving Long-Tail Video Recognitioncited by 22
2024ConjNorm: Tractable Density Estimation for Out-of-Distribution Detectioncited by 22
2022Maximum Class Separation as Inductive Bias in One Matrixcited by 21
2022When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Methodcited by 21
2022Balanced Product of Calibrated Experts for Long-Tailed Recognitioncited by 20
2023Feature Fusion from Head to Tail for Long-Tailed Visual Recognitioncited by 20
2022Improving the Intra-class Long-tail in 3D Detection via Rare Example Miningcited by 19
2023MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognitioncited by 19
2023RankMixup: Ranking-Based Mixup Training for Network Calibrationcited by 19
2024Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learningcited by 19
2024Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwardscited by 19
2023Simplifying Neural Network Training Under Class Imbalancecited by 18
2024Delving into the Trajectory Long-tail Distribution for Muti-object Trackingcited by 18
2022Region Rebalance for Long-Tailed Semantic Segmentationcited by 17
2022Label-Noise Learning with Intrinsically Long-Tailed Datacited by 17
2022Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learningcited by 17
2021Long-tail Recognition via Compositional Knowledge Transfercited by 16
2021Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Imagescited by 16

50 most cited of 212 All 212 (JSON)