Novelty detection is a fundamental task of machine learning which aims to detect abnormal ($\textit{i.e.}$ out-of-distribution (OOD)) samples. Since diffusion models have recently emerged as the de facto standard generative framework with surprising generation results, novelty detection via diffusion models has also gained much attention. Recent methods have mainly utilized the reconstruction property of in-distribution samples. However, they often suffer from detecting OOD samples that share similar background information to the in-distribution data. Based on our observation that diffusion models can \emph{project} any sample to an in-distribution sample with similar background information, we propose \emph{Projection Regret (PR)}, an efficient novelty detection method that mitigates the bias of non-semantic information. To be specific, PR computes the perceptual distance between the test image and its diffusion-based projection to detect abnormality. Since the perceptual distance often fails to capture semantic changes when the background information is dominant, we cancel out the background bias by comparing it against recursive projections. Extensive experiments demonstrate that PR outperforms the prior art of generative-model-based novelty detection methods by a significant margin.

翻译：新颖性检测是机器学习的一项基本任务，旨在检测异常（即分布外（OOD））样本。由于扩散模型最近已成为事实上的标准生成框架，并产生了令人惊讶的生成结果，因此通过扩散模型进行新颖性检测也受到了广泛关注。近期的方法主要利用了分布内样本的重建特性。然而，它们通常难以检测与分布内数据共享相似背景信息的OOD样本。基于我们的观察，即扩散模型可以将任何样本“投影”到具有相似背景信息的分布内样本，我们提出了“投影遗憾”（Projection Regret, PR），一种高效的、能够减轻非语义信息偏差的新颖性检测方法。具体来说，PR计算测试图像与其基于扩散的投影之间的感知距离以检测异常。由于当背景信息占主导地位时，感知距离通常无法捕捉语义变化，我们通过将其与递归投影进行比较来消除背景偏差。大量实验表明，PR以显著优势超越了先前基于生成模型的新颖性检测方法。