# Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition

arXiv: https://arxiv.org/abs/2109.05263 · HTML: https://mlsanity.com/paper/2109.05263/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 11 Sep 2021.

## Builds on (most cited first, 24 of 24)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration](https://mlsanity.com/paper/1910.12656/) (2019)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [What is the Effect of Importance Weighting in Deep Learning?](https://mlsanity.com/paper/1812.03372/) (2018)
- [Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning](https://mlsanity.com/paper/2002.06470/) (2020)
- [Local Temperature Scaling for Probability Calibration](https://mlsanity.com/paper/2008.05105/) (2020)
- [Deep Imbalanced Learning for Face Recognition and Attribute Prediction](https://mlsanity.com/paper/1806.00194/) (2018)
- [Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study](https://mlsanity.com/paper/2104.00676/) (2021)
- [Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference](https://mlsanity.com/paper/1909.13550/) (2019)
- [Learning and Reasoning with the Graph Structure Representation in Robotic Surgery](https://mlsanity.com/paper/2007.03357/) (2020)
- [Distillation ≈ Early Stopping? Harvesting Dark Knowledge Utilizing Anisotropic Information Retrieval For Overparameterized Neural Network](https://mlsanity.com/paper/1910.01255/) (2019)
- [Moonshine: Distilling with Cheap Convolutions](https://mlsanity.com/paper/1711.02613/) (2017)
- [Bin-wise Temperature Scaling (BTS): Improvement in Confidence Calibration Performance through Simple Scaling Techniques](https://mlsanity.com/paper/1908.11528/) (2019)
- [Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks](https://mlsanity.com/paper/1810.11586/) (2018)

## Built on by (most cited first, 19 of 19)

- [A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration](https://mlsanity.com/paper/2203.13834/) (2022)
- [Towards Improving Calibration in Object Detection Under Domain Shift](https://mlsanity.com/paper/2209.07601/) (2022)
- [Fine-Tuning is Fine, if Calibrated](https://mlsanity.com/paper/2409.16223/) (2024)
- [Multiclass Confidence and Localization Calibration for Object Detection](https://mlsanity.com/paper/2306.08271/) (2023)
- [Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection](https://mlsanity.com/paper/2303.14404/) (2023)
- [Cal-DETR: Calibrated Detection Transformer](https://mlsanity.com/paper/2311.03570/) (2023)
- [Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores](https://mlsanity.com/paper/2207.09957/) (2022)
- [EndoOOD: Uncertainty-aware Out-of-distribution Detection in Capsule Endoscopy Diagnosis](https://mlsanity.com/paper/2402.11476/) (2024)
- [Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration](https://mlsanity.com/paper/2207.08525/) (2022)
- [Average Calibration Error: A Differentiable Loss for Improved Reliability in Image Segmentation](https://mlsanity.com/paper/2403.06759/) (2024)
- [Refine and Align: Confidence Calibration through Multi-Agent Interaction in VQA](https://mlsanity.com/paper/2511.11169/) (2025)
- [PRiSM: Enhancing Low-Resource Document-Level Relation Extraction with Relation-Aware Score Calibration](https://mlsanity.com/paper/2309.13869/) (2023)
- [AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images](https://mlsanity.com/paper/2312.06106/) (2023)
- [Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement](https://mlsanity.com/paper/2505.01766/) (2025)
- [CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation](https://mlsanity.com/paper/2502.17429/) (2025)
- [Your AI-Generated Image Detector Can Secretly Achieve SOTA Accuracy, If Calibrated](https://mlsanity.com/paper/2602.01973/) (2026)
- [Dual-Branch Temperature Scaling Calibration for Long-Tailed Recognition](https://mlsanity.com/paper/2308.08366/) (2023)
- [A dual-branch model with inter- and intra-branch contrastive loss for long-tailed recognition](https://mlsanity.com/paper/2309.16135/) (2023)
- [Few-Shot Ordinal Learning for Day-Wise Freshness Estimation with Hyperspectral Fish Images](https://mlsanity.com/paper/2608.12230/) (2026)

## Abstract (arXiv)

Despite impressive accuracy, deep neural networks are often miscalibrated and tend to overly confident predictions. Recent techniques like temperature scaling (TS) and label smoothing (LS) show effectiveness in obtaining a well-calibrated model by smoothing logits and hard labels with scalar factors, respectively. However, the use of uniform TS or LS factor may not be optimal for calibrating models trained on a long-tailed dataset where the model produces overly confident probabilities for high-frequency classes. In this study, we propose class-distribution-aware TS (CDA-TS) and LS (CDA-LS) by incorporating class frequency information in model calibration in the context of long-tailed distribution. In CDA-TS, the scalar temperature value is replaced with the CDA temperature vector encoded with class frequency to compensate for the over-confidence. Similarly, CDA-LS uses a vector smoothing factor and flattens the hard labels according to their corresponding class distribution. We also integrate CDA optimal temperature vector with distillation loss, which reduces miscalibration in self-distillation (SD). We empirically show that class-distribution-aware TS and LS can accommodate the imbalanced data distribution yielding superior performance in both calibration error and predictive accuracy. We also observe that SD with an extremely imbalanced dataset is less effective in terms of calibration performance. Code is available in https://github.com/mobarakol/Class-Distribution-Aware-TS-LS.