# Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging

arXiv: https://arxiv.org/abs/2606.02339 · HTML: https://mlsanity.com/paper/2606.02339/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 57 of its 93 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 30 of 57)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning](https://mlsanity.com/paper/2505.15134/) (2025)
- [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://mlsanity.com/paper/1912.11078/) (2019)
- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation](https://mlsanity.com/paper/2004.04668/) (2020)
- [Test-Time Adaptation via Conjugate Pseudo-labels](https://mlsanity.com/paper/2207.09640/) (2022)
- [Model Collapse Demystified: The Case of Regression](https://mlsanity.com/paper/2402.07712/) (2024)
- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction](https://mlsanity.com/paper/2306.00650/) (2023)
- [Strong Model Collapse](https://mlsanity.com/paper/2410.04840/) (2024)

## Abstract (arXiv)

Entropy minimization (EM) is the dominant objective for test-time adaptation, yet its failure mode, model collapse, remains poorly understood. In this work, we show that distribution shifts can cause feature clusters corresponding to distinct classes in the model's representation space to merge, while the decision boundary remains fixed. This induces a systematic skew in the predicted class distribution, referred to as prediction bias. Prediction bias refers to a shift in the predicted class distribution, with some classes overrepresented and others suppressed. We show that entropy minimization amplifies this prediction bias by tightening the existing clusters, reinforcing the incorrect groupings until all predictions collapse to a trivial solution. Next, to demonstrate the significance of prediction bias and mitigate it, we further propose Distribution Shift Bias Reduction (DSBR), a bias-correcting objective that specifically targets this failure mode by equalizing the contribution of each predicted class to the unsupervised entropy minimization loss. To study this failure mode, we design suitable adaptation settings using four medical-imaging datasets and additionally evaluate on ImageNet-C. We find that DSBR consistently stabilizes test-time adaptation, prevents model collapse, and matches or outperforms state-of-the-art methods. Moreover, DSBR operates solely at test-time.