Pith. sign in

REVIEW 4 cited by

Deep Nearest Neighbor Anomaly Detection

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 2002.10445 v1 pith:M3Z2OAPI submitted 2020-02-24 cs.LG cs.CVstat.ML

Liron Bergman , Niv Cohen , Yedid Hoshen This is my paper
classification cs.LGcs.CVstat.ML
keywords methodsself-supervisedanomalydeepdetectionfeaturesimagenetnearest
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Nearest neighbors is a successful and long-standing technique for anomaly detection. Significant progress has been recently achieved by self-supervised deep methods (e.g. RotNet). Self-supervised features however typically under-perform Imagenet pre-trained features. In this work, we investigate whether the recent progress can indeed outperform nearest-neighbor methods operating on an Imagenet pretrained feature space. The simple nearest-neighbor based-approach is experimentally shown to outperform self-supervised methods in: accuracy, few shot generalization, training time and noise robustness while making fewer assumptions on image distributions.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 109 citations worldwide. Full citation record

  1. SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark

    cs.CV 2025-06 conditional novelty 7.0 of 10

    SiM3D provides a multiview, multimodal 3D anomaly detection benchmark with single-instance training and synthetic-to-real evaluation, showing adapted 2D methods often beat multimodal 3D methods on the new voxel-based task.

  2. Separating Knowledge and Perception with Procedural Data

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Representation models trained only on procedural graphics plus a nearest-neighbor memory of real photos classify and segment real images at near-real-data accuracy while keeping all real data inside the memory.

  3. How to Use Graph Data in the Wild to Help Graph Anomaly Detection?

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Wild-GAD selects relevant and diverse external graphs via a target-trained model and trains the detector on them, reporting large accuracy gains over baselines.

  4. HomographyAD: Deep Anomaly Detection Using Self Homography Learning

    cs.CV 2025-06 reject novelty 5.0 of 10

    Input alignment plus self-supervised homography regression fine-tuning improves pretrained-feature anomaly detection on MVTec object classes, but hurts texture classes.

Pith tools