SpurCon：用于缓解医学成像中虚假线索的加权监督对比学习

中文摘要 AI 辅助

尽管深度神经网络在视觉识别领域取得了快速进展，但由于可靠性和鲁棒性方面的担忧，其在高风险医疗应用中的采用仍然有限。模型可能会利用虚假相关性，尤其是在医学成像中，设备或治疗伪影常与病理共存。在小型或不平衡数据集中，此类线索会进一步降低最差组的性能并破坏临床信任。为解决这些问题，需应对两大挑战：识别特定于数据集的虚假线索（通常需要领域知识），以及减轻对这些线索的依赖。为同时应对这两点，我们提出了SpurCon，这是一个基于新型监督对比损失公式的轻量级框架，利用可用元数据和预测的虚假标签来增强鲁棒性。我们引入了一种无需网络训练的快速少样本流程，使用少量专家标注样本来估计虚假标签。随后，我们提出了加权监督对比目标WtSupCon，通过分配依赖于[病理、虚假、元数据]组合的样本特定权重来重塑表示几何结构。例如，仅在虚假标签上存在差异的样本会被分配最高权重。这使得具有相同元数据和病理、仅在预测虚假标签上存在差异的图像能产生高度相似的表示。我们的方法基于预训练的图像编码器（如BiomedCLIP）运行，仅训练轻量级投影头。我们在合成场景以及Waterbirds、CheXpert（胸部X射线分类数据集）和ISIC 2020（皮肤癌分类数据集）上评估了SpurCon。我们的方法实现了最佳的虚假线索缓解性能，在多个数据集上很好地平衡了最差组准确率和总体准确率。

英文摘要

Despite the rapid progress of deep neural networks in visual recognition, their adoption in high-risk medical applications remains limited due to reliability and robustness concerns. Models may exploit spurious correlations, particularly in medical imaging, where devices or treatment artifacts often co-occur with pathology. In small or imbalanced datasets, such cues further reduce worst-group performance and undermine clinical trust. To solve these issues, two major challenges should be addressed: identifying dataset-specific spurious cues, which typically require domain knowledge, and mitigating reliance on them. To tackle both, we propose SpurCon, a lightweight framework based on a novel supervised contrastive loss formulation that leverages available metadata and predicted spurious labels to enhance robustness. We introduce a fast few-shot procedure, without network training, to estimate spurious labels using a small number of expert-annotated samples. We then propose a weighted supervised contrastive objective, WtSupCon, that reshapes the representation geometry by assigning sample-specific weights that depend on the [pathology, spurious, metadata] combination. For example, the highest weight is assigned to samples that differ only in their spurious label. This yields highly similar representations for images with the same metadata and pathology, differing only in the predicted spurious label. Our method operates on pretrained image encoders (such as BiomedCLIP) and trains only a lightweight projection head. We evaluate SpurCon on a synthetic setting and on Waterbirds, CheXpert, a chest X-ray classification dataset, and ISIC 2020, a skin cancer classification dataset. Our approach delivers the best spurious-mitigation performance, balancing well worst-group and overall accuracy on multiple datasets.

发表机构

• Viterbi Faculty of Electrical and Computer Engineering, Technion - Israel Institute of Technology（以色列理工学院维特比电气与计算机工程学院）

机构由 AI 辅助整理，请以论文原文为准。