# ReMix: Calibrated Resampling for Class Imbalance in Deep learning

arXiv: https://arxiv.org/abs/2012.02312 · HTML: https://mlsanity.com/paper/2012.02312/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 10 of 10)

- [DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data](https://mlsanity.com/paper/2105.02340/) (2021)
- [MedConv: Convolutions Beat Transformers on Long-Tailed Bone Density Prediction](https://mlsanity.com/paper/2502.00631/) (2025)
- [Understanding CNN Fragility When Learning With Imbalanced Data](https://mlsanity.com/paper/2210.09465/) (2022)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Set Learning for Accurate and Calibrated Models](https://mlsanity.com/paper/2307.02245/) (2023)
- [Towards Understanding How Data Augmentation Works with Imbalanced Data](https://mlsanity.com/paper/2304.05895/) (2023)
- [MCRAGE: Synthetic Healthcare Data for Fairness](https://mlsanity.com/paper/2310.18430/) (2023)
- [Optimizing for ROC Curves on Class-Imbalanced Data by Training over a Family of Loss Functions](https://mlsanity.com/paper/2402.05400/) (2024)
- [Training Over a Distribution of Hyperparameters for Enhanced Performance and Adaptability on Imbalanced Classification](https://mlsanity.com/paper/2410.03588/) (2024)
- [The Hidden Cost of Resampling: How Imbalance Correction Degrades Probability Calibration in Tree Ensembles](https://mlsanity.com/paper/2606.29720/) (2026)

## Abstract (arXiv)

Class imbalance is a problem of significant importance in applied deep learning where trained models are exploited for decision support and automated decisions in critical areas such as health and medicine, transportation, and finance. The challenge of learning deep models from imbalanced training data remains high, and the state-of-the-art solutions are typically data dependent and primarily focused on image data. Real-world imbalanced classification problems, however, are much more diverse thus necessitating a general solution that can be applied to tabular, image and text data. In this paper, we propose ReMix, a training technique that leverages batch resampling, instance mixing and soft-labels to enable the induction of robust deep models for imbalanced learning. Our results show that dense nets and CNNs trained with ReMix generally outperform the alternatives according to the g-mean and are better calibrated according to the balanced Brier score.