Out-of-Distribution Detection with Deep Nearest Neighbors

Yiyou Sun · Yifei Ming · Jerry Zhu · Yixuan Li

Hall E #1002

Keywords: [ DL: Algorithms ] [ SA: Trustworthy Machine Learning ]

[ Abstract ]
[ Poster [ Paper PDF
Wed 20 Jul 3:30 p.m. PDT — 5:30 p.m. PDT
Spotlight presentation: SA: Trustworthy Machine Learning
Wed 20 Jul 10:15 a.m. PDT — 11:45 a.m. PDT


Out-of-distribution (OOD) detection is a critical task for deploying machine learning models in the open world. Distance-based methods have demonstrated promise, where testing samples are detected as OOD if they are relatively far away from in-distribution (ID) data. However, prior methods impose a strong distributional assumption of the underlying feature space, which may not always hold. In this paper, we explore the efficacy of non-parametric nearest-neighbor distance for OOD detection, which has been largely overlooked in the literature. Unlike prior works, our method does not impose any distributional assumption, hence providing stronger flexibility and generality. We demonstrate the effectiveness of nearest-neighbor-based OOD detection on several benchmarks and establish superior performance. Under the same model trained on ImageNet-1k, our method substantially reduces the false positive rate (FPR@TPR95) by 24.77% compared to a strong baseline SSD+, which uses a parametric approach Mahalanobis distance in detection. Code is available:

Chat is not available.