# Test-time Adaptation with Calibration of Medical Image Classification Nets for Label Distribution Shift

arXiv: https://arxiv.org/abs/2207.00769 · HTML: https://mlsanity.com/paper/2207.00769/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 2 Jul 2022.

## Builds on (most cited first, 13 of 13)

- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Long-tailed Recognition by Routing Diverse Distribution-Aware Experts](https://mlsanity.com/paper/2010.01809/) (2020)
- [Disentangling Label Distribution for Long-tailed Visual Recognition](https://mlsanity.com/paper/2012.00321/) (2020)
- [Regularized Learning for Domain Adaptation under Label Shifts](https://mlsanity.com/paper/1903.09734/) (2019)
- [Online Adaptation to Label Distribution Shift](https://mlsanity.com/paper/2107.04520/) (2021)
- [Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels](https://mlsanity.com/paper/2005.08455/) (2020)
- [Probabilistic Machine Learning for Healthcare](https://mlsanity.com/paper/2009.11087/) (2020)
- [Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images](https://mlsanity.com/paper/1806.01357/) (2018)
- [Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection](https://mlsanity.com/paper/2110.14019/) (2021)
- [Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches](https://mlsanity.com/paper/1801.03230/) (2018)
- [Attention-based Multi-scale Gated Recurrent Encoder with Novel Correlation Loss for COVID-19 Progression Prediction](https://mlsanity.com/paper/2107.08330/) (2021)
- [COVID-MTL: Multitask Learning with Shift3D and Random-weighted Loss for Automated Diagnosis and Severity Assessment of COVID-19](https://mlsanity.com/paper/2012.05509/) (2020)

## Built on by (most cited first, 20 of 20)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Robust Test-Time Adaptation in Dynamic Scenarios](https://mlsanity.com/paper/2303.13899/) (2023)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification](https://mlsanity.com/paper/2306.02544/) (2023)
- [Medical Image Segmentation with InTEnt: Integrated Entropy Weighting for Single Image Test-Time Adaptation](https://mlsanity.com/paper/2402.09604/) (2024)
- [Multi-Head Multi-Loss Model Calibration](https://mlsanity.com/paper/2303.01099/) (2023)
- [Navigating Distribution Shifts in Medical Image Analysis: A Survey](https://mlsanity.com/paper/2411.05824/) (2024)
- [Automatic dataset shift identification to support safe deployment of medical imaging AI](https://mlsanity.com/paper/2411.07940/) (2024)
- [Deployment of Image Analysis Algorithms under Prevalence Shifts](https://mlsanity.com/paper/2303.12540/) (2023)
- [Daily Physical Activity Monitoring -- Adaptive Learning from Multi-source Motion Sensor Data](https://mlsanity.com/paper/2405.16395/) (2024)
- [Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies](https://mlsanity.com/paper/2505.22829/) (2025)
- [Multi Task Consistency Guided Source-Free Test-Time Domain Adaptation Medical Image Segmentation](https://mlsanity.com/paper/2310.11766/) (2023)
- [Sample-Aware Test-Time Adaptation for Medical Image-to-Image Translation](https://mlsanity.com/paper/2508.00766/) (2025)
- [Bayesian-based Online Label Shift Estimation with Dynamic Dirichlet Priors](https://mlsanity.com/paper/2511.18615/) (2025)
- [DART3: Leveraging Distance for Test Time Adaptation in Person Re-Identification](https://mlsanity.com/paper/2505.18337/) (2025)
- [Impact of domain adaptation in deep learning for medical image classifications](https://mlsanity.com/paper/2602.09355/) (2026)
- [When Can Test-Time Adaptation Help Zero-Shot CT Vision-Language Models?](https://mlsanity.com/paper/2607.15556/) (2026)
- [Improving Calibration of Black-Box Radiology AI Using Test-Time Augmentation](https://mlsanity.com/paper/2609.29931/) (2026)

## Abstract (arXiv)

Class distribution plays an important role in learning deep classifiers. When the proportion of each class in the test set differs from the training set, the performance of classification nets usually degrades. Such a label distribution shift problem is common in medical diagnosis since the prevalence of disease vary over location and time. In this paper, we propose the first method to tackle label shift for medical image classification, which effectively adapt the model learned from a single training label distribution to arbitrary unknown test label distribution. Our approach innovates distribution calibration to learn multiple representative classifiers, which are capable of handling different one-dominating-class distributions. When given a test image, the diverse classifiers are dynamically aggregated via the consistency-driven test-time adaptation, to deal with the unknown test label distribution. We validate our method on two important medical image classification tasks including liver fibrosis staging and COVID-19 severity prediction. Our experiments clearly show the decreased model performance under label shift. With our method, model performance significantly improves on all the test datasets with different label shifts for both medical image diagnosis tasks.