患病率校准作为捷径缓解方法
Prevalence calibration as shortcut mitigation
浏览论文内容
中文总结 AI 辅助
本研究将捷径学习重新定义为校准问题，提出两种与编码器无关的患病率均衡校准方法，在胸管气胸基准上显著提升性能，并揭示了捷径依赖损害分类头而非表示。\n
中文摘要 AI 辅助
捷径学习指的是分类器利用虚假相关性而非诊断特征的普遍情况。现有的缓解策略大多旨在学习捷径不变的表示；其实证成功有限，且无法应用于使用冻结基础模型编码器的分类器。我们提出将捷径学习从根本上重新定义为校准问题：无约束学习隐式地将每个捷径组校准到其训练集的疾病患病率，使得所得分类器必然在一个组中过度自信而在另一个组中信心不足。基于这一见解，我们通过两种与编码器无关的方法——一种处理中正则化器和一种事后患病率均衡重校准步骤——在捷径组之间进行患病率均衡校准。在CheXpert和SIIM-ACR上的胸管气胸基准测试中，涵盖微调CNN和冻结基础模型骨干，两种方法均大幅优于所有基线。对标准ERM训练的DenseNet进行事后重校准，将错位组的AUROC从0.23提升至0.73，表明捷径依赖削弱的是分类头而非底层表示。除了两种新的最先进的捷径缓解方法外，我们的发现更根本地将捷径学习与校准理论和算法公平性联系起来。
英文摘要
Shortcut learning denotes the widespread situation in which a classifier exploits spurious correlations rather than diagnostic features. Existing mitigation strategies mostly aim to learn shortcut-invariant representations; their empirical success is limited and they cannot be applied to classifiers using frozen foundation model encoders. We propose to reframe shortcut learning as fundamentally a calibration problem: unconstrained learning implicitly calibrates each shortcut group to its training set disease prevalence, rendering the resulting classifier necessarily over-confident in one group and under-confident in the other. Building on this insight, we prevalence-equalize calibration between shortcut groups through two encoder-agnostic methods, an in-processing regularizer and a post-hoc prevalence-equalized recalibration step. Across chest-drain-pneumothorax benchmarks on CheXpert and SIIM-ACR, spanning fine-tuned CNNs and frozen foundation-model backbones, both methods substantially outperform all baselines. Post-hoc recalibration of a standard ERM-trained DenseNet raises misaligned-group AUROC from 0.23 to 0.73, indicating that shortcut reliance degrades the classification head rather than the underlying representation. Besides two new state-of-the-art shortcut mitigation approaches, our findings more fundamentally connect shortcut learning to calibration theory and algorithmic fairness.
发表机构
- Universität Bremen（不来梅大学）
- Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学MEVIS研究所）
机构由 AI 辅助整理，请以论文原文为准。
