Unsupervised Anomaly Detection (UAD) techniques aim to identify and localize anomalies without relying on annotations, only leveraging a model trained on a dataset known to be free of anomalies. Diffusion models learn to modify inputs $x$ to increase the probability of it belonging to a desired distribution, i.e., they model the score function $\nabla_x \log p(x)$. Such a score function is potentially relevant for UAD, since $\nabla_x \log p(x)$ is itself a pixel-wise anomaly score. However, diffusion models are trained to invert a corruption process based on Gaussian noise and the learned score function is unlikely to generalize to medical anomalies. This work addresses the problem of how to learn a score function relevant for UAD and proposes DISYRE: Diffusion-Inspired SYnthetic REstoration. We retain the diffusion-like pipeline but replace the Gaussian noise corruption with a gradual, synthetic anomaly corruption so the learned score function generalizes to medical, naturally occurring anomalies. We evaluate DISYRE on three common Brain MRI UAD benchmarks and substantially outperform other methods in two out of the three tasks.

翻译：无监督异常检测技术旨在无需依赖标注的情况下识别和定位异常，仅利用在已知无异常数据集上训练的模型。扩散模型通过修改输入$x$来增加其属于目标分布的概率，即它们建模得分函数$\nabla_x \log p(x)$。该得分函数对无监督异常检测具有潜在相关性，因为$\nabla_x \log p(x)$本身即为逐像素的异常得分。然而，扩散模型被训练用于逆转基于高斯噪声的损坏过程，其学习的得分函数难以泛化至医学异常。本研究针对如何学习与无监督异常检测相关的得分函数这一难题，提出了DISYRE：扩散启发式合成修复。我们保留了类似扩散的流水线，但将高斯噪声损坏替换为逐步的合成异常损坏，使得学习到的得分函数能够泛化至自然发生的医学异常。我们在三个常见脑部MRI无监督异常检测基准上对DISYRE进行评估，并在三项任务中的两项上显著优于其他方法。