Saved in:
Bibliographic Details
Main Authors: Aizawa, Hiroaki, Naito, Yuta, Fukuda, Kohei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.18723
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915463525564416
author Aizawa, Hiroaki
Naito, Yuta
Fukuda, Kohei
author_facet Aizawa, Hiroaki
Naito, Yuta
Fukuda, Kohei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18723
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Class-wise Flooding Regularization for Imbalanced Image Classification
Aizawa, Hiroaki
Naito, Yuta
Fukuda, Kohei
Computer Vision and Pattern Recognition
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.
title Class-wise Flooding Regularization for Imbalanced Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.18723