将医学异常检测特征投影到双曲空间，提升识别精度与鲁棒性
Is Hyperbolic Space All You Need for Medical Anomaly Detection?
- 把网络特征投射到双曲空间，利用其层次结构建模能力
- 在多个数据集上图像和像素级的AUROC均显著提升
- 尤其适合健康样本稀缺的少样本场景
医学异常检测在数据稀缺和标注受限背景下展现出巨大潜力。传统方法在欧氏空间中提取预训练网络不同层的特征，但欧氏表示难以有效捕捉特征间的层次关系，导致检测性能不佳。本文提出一种新颖而简洁的方法：将特征表示投影至双曲空间，依据置信度聚合后分类为健康或异常。实验表明，双曲空间在多个医学基准数据集上持续优于欧氏框架，在图像和像素级别均取得更高AUROC得分。此外，该方法对参数变化具有鲁棒性，且在少样本场景下表现优异，即健康样本稀少时仍能保持高精度。这些结果凸显了双曲空间在医学异常检测中的强大潜力。
原文摘要 · Abstract (English)
Medical anomaly detection has emerged as a promising solution to challenges in data availability and labeling constraints. Traditional methods extract features from different layers of pre-trained networks in Euclidean space; however, Euclidean representations fail to effectively capture the hierarchical relationships within these features, leading to suboptimal anomaly detection performance. We propose a novel yet simple approach that projects feature representations into hyperbolic space, aggregates them based on confidence levels, and classifies samples as healthy or anomalous. Our experiments demonstrate that hyperbolic space consistently outperforms Euclidean-based frameworks, achieving higher AUROC scores at both image and pixel levels across multiple medical benchmark datasets. Additionally, we show that hyperbolic space exhibits resilience to parameter variations and excels in few-shot scenarios, where healthy images are scarce. These findings underscore the potential of hyperbolic space as a powerful alternative for medical anomaly detection. The project website can be found at https://hyperbolic-anomalies.github.io
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。