用狄利克雷过程混合模型聚类DINO特征，高效实现医学影像无监督异常检测。
Anomaly Detection by Clustering DINO Embeddings using a Dirichlet Process Mixture
- 用非参数的狄利克雷过程混合模型自动学习正常特征分布
- 在医疗影像上达到优秀检测性能，推理时间至少减少一半
- 归一化DINO特征更贴近解剖结构，适合异常检测
本文利用基础模型生成的语义嵌入进行医学影像的无监督异常检测。针对小数据集，可直接使用正常特征记忆库进行检测，但对大规模数据集计算开销过大。为此，我们提出用狄利克雷过程混合模型（DPMM）建模DINOv2嵌入的正常分布，该模型能根据数据自动调整分量数量。不采用记忆库，而是以组件中心与嵌入间的相似度作为异常评分函数，生成粗粒度异常分割掩码。实验表明，尽管DINOv2在自然图像上训练，其嵌入在医疗影像基准测试中表现优异，且推理时间至少减半。进一步分析显示，归一化后的DINOv2嵌入即使存在异常也更符合解剖结构，是理想的异常检测表示。代码已开源：https://github.com/NicoSchulthess/anomalydino-dpmm。
原文摘要 · Abstract (English)
In this work, we leverage informative embeddings from foundational models for unsupervised anomaly detection in medical imaging. For small datasets, a memory-bank of normative features can directly be used for anomaly detection which has been demonstrated recently. However, this is unsuitable for large medical datasets as the computational burden increases substantially. Therefore, we propose to model the distribution of normative DINOv2 embeddings with a Dirichlet Process Mixture model (DPMM), a non-parametric mixture model that automatically adjusts the number of mixture components to the data at hand. Rather than using a memory bank, we use the similarity between the component centers and the embeddings as anomaly score function to create a coarse anomaly segmentation mask. Our experiments show that through DPMM embeddings of DINOv2, despite being trained on natural images, achieve very competitive anomaly detection performance on medical imaging benchmarks and can do this while at least halving the computation time at inference. Our analysis further indicates that normalized DINOv2 embeddings are generally more aligned with anatomical structures than unnormalized features, even in the presence of anomalies, making them great representations for anomaly detection. The code is available at https://github.com/NicoSchulthess/anomalydino-dpmm.
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。