k-NNN: Nearest Neighbors of Neighbors for Anomaly Detection

Ori Nizan, Ayellet Tal

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Anomaly detection aims at identifying images that deviate significantly from the norm. We focus on algorithms that embed the normal training examples in space and, when given a test image, detect anomalies based on the features' distance to the k-nearest training neighbors. We propose a new operator that takes into account the varying structure & importance of the features in the embedding space. Interestingly, this is achieved by considering not only the nearest neighbors but also the neighbors of these neighbors (k-NNN). Our results demonstrate that by simply replacing the nearest neighbor component in existing algorithms with our k-NNN, while leaving the rest of the algorithms unchanged, the performance of each algorithm is improved. This holds true for both common homogeneous datasets, such as specific flowers, as well as for more diverse datasets.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2024
Pages1005-1014
Number of pages10
ISBN (Electronic)9798350370287
DOIs
StatePublished - 2024
Event2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2024 - Waikoloa, United States
Duration: 4 Jan 20248 Jan 2024

Publication series

NameProceedings - 2024 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2024

Conference

Conference2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2024
Country/TerritoryUnited States
CityWaikoloa
Period4/01/248/01/24

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Media Technology

Fingerprint

Dive into the research topics of 'k-NNN: Nearest Neighbors of Neighbors for Anomaly Detection'. Together they form a unique fingerprint.

Cite this