Timezone: »

Out-of-Distribution Detection with Deep Nearest Neighbors
Yiyou Sun · Yifei Ming · Jerry Zhu · Sharon Li

Wed Jul 20 10:50 AM -- 10:55 AM (PDT) @ Room 309

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: https://github.com/deeplearning-wisc/knn-ood.

Author Information

Yiyou Sun (University of Wisconsin Madison)
Yifei Ming (University of Wisconsin-Madison)
Jerry Zhu (University of Wisconsin-Madison)
Sharon Li (University of Wisconsin-Madison)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors