# Class-wise Flooding Regularization for Imbalanced Image Classification

arXiv: https://arxiv.org/abs/2508.18723 · HTML: https://mlsanity.com/paper/2508.18723/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning](https://mlsanity.com/paper/2202.03599/) (2022)
- [Do We Need Zero Training Loss After Achieving Zero Training Error?](https://mlsanity.com/paper/2002.08709/) (2020)
- [Soft ascent-descent as a stable and flexible alternative to flooding](https://mlsanity.com/paper/2310.10006/) (2023)
- [AdaFlood: Adaptive Flood Regularization](https://mlsanity.com/paper/2311.02891/) (2023)

## Abstract (arXiv)

The purpose of training neural networks is to achieve high generalization performance on unseen inputs. However, when trained on imbalanced datasets, a model's prediction tends to favor majority classes over minority classes, leading to significant degradation in the recognition performance of minority classes. To address this issue, we propose class-wise flooding regularization, an extension of flooding regularization applied at the class level. Flooding is a regularization technique that mitigates overfitting by preventing the training loss from falling below a predefined threshold, known as the flooding level, thereby discouraging memorization. Our proposed method assigns a class-specific flooding level based on class frequencies. By doing so, it suppresses overfitting in majority classes while allowing sufficient learning for minority classes. We validate our approach on imbalanced image classification. Compared to conventional flooding regularizations, our method improves the classification performance of minority classes and achieves better overall generalization.