论文标题
Fairdisco：通过脱离对比学习，皮肤病学方面的AI更公平
FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning
论文作者
论文摘要
深度学习模型在自动化皮肤病变诊断方面取得了巨大成功。但是，在这些模型的预测中，种族差异通常不足以说明深色皮肤类型的病变，并且诊断准确性较低，因此受到很少的关注。在本文中，我们提出了Fairdisco，这是一个通过对比度学习的解开深度学习框架，它利用一个额外的网络分支来删除敏感属性，即从表示公平的表示和另一个对比分支来增强特征提取的敏感属性信息。我们将Fairdisco与三种公平方法进行了比较，即重新采样，重新加权和属性 - 在两个新发布的具有不同皮肤类型的皮肤病变数据集上：Fitzpatrick17k和多样的皮肤病学图像（DDI）。我们将两个基于公平的指标DPM和EOM适应我们的多个类别和敏感属性任务，从而突出了皮肤病变分类的皮肤型偏差。广泛的实验评估证明了Fairdisco的有效性，并在皮肤病变分类任务上更公平，更出色。
Deep learning models have achieved great success in automating skin lesion diagnosis. However, the ethnic disparity in these models' predictions, where lesions on darker skin types are usually underrepresented and have lower diagnosis accuracy, receives little attention. In this paper, we propose FairDisCo, a disentanglement deep learning framework with contrastive learning that utilizes an additional network branch to remove sensitive attributes, i.e. skin-type information from representations for fairness and another contrastive branch to enhance feature extraction. We compare FairDisCo to three fairness methods, namely, resampling, reweighting, and attribute-aware, on two newly released skin lesion datasets with different skin types: Fitzpatrick17k and Diverse Dermatology Images (DDI). We adapt two fairness-based metrics DPM and EOM for our multiple classes and sensitive attributes task, highlighting the skin-type bias in skin lesion classification. Extensive experimental evaluation demonstrates the effectiveness of FairDisCo, with fairer and superior performance on skin lesion classification tasks.
