针对数据不平衡问题，提出按类别设定不同正则化阈值，提升少数类识别效果。
Class-wise Flooding Regularization for Imbalanced Image Classification
- 为不同类别设置差异化正则化阈值，抑制多数类过拟合。
- 在不平衡数据上显著提升少数类准确率，整体泛化性能更优。
- 适合处理类别不均衡的图像分类任务，如医疗影像识别。
训练神经网络的目标是实现对未见输入的良好泛化性能。然而，在不平衡数据集上训练时，模型预测往往偏向多数类，导致少数类识别性能严重下降。为此，我们提出类别级洪水正则化，将洪水正则化扩展至类别层面。洪水正则化通过防止训练损失低于预设阈值（即洪水水平）来缓解过拟合，抑制记忆化现象。所提方法根据类别频率分配类别专属的洪水水平，从而抑制多数类过拟合，同时保障少数类充分学习。我们在不平衡图像分类任务上验证了该方法，相比传统洪水正则化，本方法显著提升了少数类分类性能，并实现了更好的整体泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。