解决医学诊断中的类别特征偏差，提升模型泛化能力
Class Unbiasing for Generalization in Medical Diagnosis
- 设计不平等损失函数，确保各类别贡献均衡的分类损失
- 结合加权分布鲁棒优化，在类别不平衡下仍有效缓解偏差
- 适用于医疗图像诊断，尤其对少数类表现提升明显
医学诊断可能因偏差而失败。本文识别出类别特征偏差——模型可能依赖仅与部分类别强相关的特征，导致性能偏倚且在其他类别上泛化能力差。我们旨在训练一个类别无偏模型（Cls-unbias），同时缓解类别不平衡和类别特征偏差。具体提出一种类别不平等损失，促进正类与负类样本对分类损失的等贡献。进一步提出类别加权的分布鲁棒优化目标，通过提升表现较差类别的权重来增强不平等损失在类别不平衡下的有效性。在合成与真实世界数据集上，实验证明类别特征偏差会负面影响模型性能。所提方法能有效缓解两类偏差，从而提升模型泛化能力。
原文摘要 · Abstract (English)
Medical diagnosis might fail due to bias. In this work, we identified class-feature bias, which refers to models' potential reliance on features that are strongly correlated with only a subset of classes, leading to biased performance and poor generalization on other classes. We aim to train a class-unbiased model (Cls-unbias) that mitigates both class imbalance and class-feature bias simultaneously. Specifically, we propose a class-wise inequality loss which promotes equal contributions of classification loss from positive-class and negative-class samples. We propose to optimize a class-wise group distributionally robust optimization objective-a class-weighted training objective that upweights underperforming classes-to enhance the effectiveness of the inequality loss under class imbalance. Through synthetic and real-world datasets, we empirically demonstrate that class-feature bias can negatively impact model performance. Our proposed method effectively mitigates both class-feature bias and class imbalance, thereby improving the model's generalization ability.
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。