AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Out-of-Distribution Detection with Deep Nearest Neighbors

Yiyou Sun, Yifei Ming, Xiaojin Zhu, Yixuan Li

ICML 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 57 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace Mahalanobis scoring with nearest-neighbor distanceCIFAR-10 KNN with cross-entropy embeddings · CIFAR-10, average across OOD datasetsFPR95: 37.94 -> 29.15Improved
Use nearest-neighbor scoring instead of SSD+'s Mahalanobis scoringCIFAR-10 SupCon model · CIFAR-10, average across OOD datasetsFPR95: 16.52 -> 11.07Improved
Train the KNN detector with SupCon rather than cross-entropy embeddings (ablation)CIFAR-10 KNN · CIFAR-10 OOD datasetsFPR95Improved
Use 1% rather than 100% of ID training data for neighbor search (ablation)ImageNet-1k KNN+ · ImageNet-1k, average across OOD datasetsFPR95: 38.47 -> 39.18Hurt
Normalize penultimate-layer features before calculating neighbor distances (ablation)ImageNet KNN · ImageNet-1k OOD datasetsFPR95: 61.05%Improved
Use penultimate-layer features rather than projection-head features (ablation)ImageNet KNN+ · ImageNet-1k OOD datasetsFPR95Improved
Use the k-th-neighbor distance rather than the averaged k-neighbor distance (ablation)ImageNet KNN+ · ImageNet-1k OOD datasetsFPR95No clear effect
Apply activation rectification (ReAct) (ablation)ImageNet KNN+ · ImageNet-1k, average across OOD datasetsFPR95: 38.47 -> 26.45Improved
Replace SSD+ scoring with nearest-neighbor scoringCIFAR-10 SupCon model · LSUN-FIX, ImageNet-FIX, ImageNet-R, and CIFAR-100 OODFPR95: 29.86 -> 21.52; 32.26 -> 25.92; 45.62 -> 29.92; 45.50 -> 38.83Improved
Replace Mahalanobis scoring with nearest-neighbor scoringViT-B/16 fine-tuned on ImageNet-1k · iNaturalist, SUN, Places, and TexturesFPR95: 17.56 -> 7.30; 80.51 -> 48.40; 84.12 -> 56.46; 70.51 -> 39.91Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy