Unsupervised out-of-distribution detection (OOD) seeks to identify out-of-domain data by learning only from unlabeled in-domain data. We present a novel approach for this task - Lift, Map, Detect (LMD) - that leverages recent advancement in diffusion models. Diffusion models are one type of generative models. At their core, they learn an iterative denoising process that gradually maps a noisy image closer to their training manifolds. LMD leverages this intuition for OOD detection. Specifically, LMD lifts an image off its original manifold by corrupting it, and maps it towards the in-domain manifold with a diffusion model. For an out-of-domain image, the mapped image would have a large distance away from its original manifold, and LMD would identify it as OOD accordingly. We show through extensive experiments that LMD achieves competitive performance across a broad variety of datasets.

翻译：无监督分布外检测（OOD）旨在仅通过无标记域内数据学习并识别域外数据。我们针对该任务提出了一种新型方法——提升、映射、检测（LMD）——该方法利用了扩散模型的最新进展。扩散模型是一类生成模型，其核心机制是学习一个迭代去噪过程，逐步将带噪图像映射至其训练流形。LMD 利用这一直觉进行OOD检测：具体而言，LMD 通过破坏图像使其脱离原始流形，再借助扩散模型将其映射至域内流形。对于域外图像，映射后的图像与原始流形距离较大，LMD 将据此将其识别为OOD。我们通过大量实验表明，LMD 在多种数据集上均取得了具有竞争力的性能。