Pith. sign in

REVIEW 5 cited by

Out-of-Distribution Detection with Deep Nearest Neighbors

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2204.06507 v3 pith:PHX7IDJT submitted 2022-04-13 cs.LG cs.CV

Yiyou Sun , Yifei Ming , Xiaojin Zhu , Yixuan Li This is my paper · ORCID
classification cs.LGcs.CV
keywords detectionassumptiondistancedistributionalimposemethodmethodsout-of-distribution
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Representation Trajectories Matters: Complementary Evidence for OOD Detection and Image Classification

    cs.CV 2026-07 accept novelty 6.0 of 10

    Recording how an image's representation evolves block-by-block, relative to learned class routes, improves OOD detection in 131/152 comparisons and clean classification in 71/72 model–dataset cases.

  2. Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration

    cs.LG 2026-07 conditional novelty 6.0 of 10

    In adaptive OOD detection, bank impurity follows a mean-field urn law whose kernel slope acts as a reproduction number; a frozen-reserve gate removes the supercritical collapse, and a two-world theorem caps label-free...

  3. Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Aleatoric uncertainty selects between counterfactual and feature-importance explanations, epistemic uncertainty rejects unreliable explanations, and correlation experiments support the rule.

  4. FindMeIfYouCan: Bringing Open Set metrics to $\textit{near} $, $ \textit{far} $ and $\textit{farther}$ Out-of-Distribution Object Detection

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A new OOD object detection benchmark with near, far, and farther splits and open-set metrics shows close unknown objects are found more often but are also more frequently mistaken for known objects.

  5. Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare

    cs.CL 2025-08 conditional novelty 5.0 of 10

    An energy-based scoring head trained on dense embeddings improves abstention decisions for medical RAG systems on semantically hard out-of-distribution queries compared to softmax and kNN baselines.

Pith tools