Models trained with empirical risk minimization (ERM) are known to learn to rely on spurious features, i.e., their prediction is based on undesired auxiliary features which are strongly correlated with class labels but lack causal reasoning. This behavior particularly degrades accuracy in groups of samples of the correlated class that are missing the spurious feature or samples of the opposite class but with the spurious feature present. The recently proposed Deep Feature Reweighting (DFR) method improves accuracy of these worst groups. Based on the main argument that ERM mods can learn core features sufficiently well, DFR only needs to retrain the last layer of the classification model with a small group-balanced data set. In this work, we examine the applicability of DFR to realistic data in the medical domain. Furthermore, we investigate the reasoning behind the effectiveness of last-layer retraining and show that even though DFR has the potential to improve the accuracy of the worst group, it remains susceptible to spurious correlations.

翻译：基于经验风险最小化（ERM）训练的模型往往会依赖虚假特征进行预测，即其决策基于与类别标签高度相关但缺乏因果关系的非目标辅助特征。这种特性尤其会降低两类样本的准确率：一类是缺失虚假特征的相关类别样本，另一类是存在虚假特征但属于相反类别的样本。近期提出的深度特征重加权（DFR）方法能有效提升这些最差组别的准确率。基于ERM模型已能充分学习核心特征这一主要论点，DFR只需使用少量组平衡数据集重新训练分类模型的最后一层。本研究在医学领域的真实数据上检验了DFR的适用性，并深入探究了末层重训练有效性的内在机理。结果表明，尽管DFR具有提升最差组别准确率的潜力，但其仍会受虚假相关性影响。