Locally varying distance transform for unsupervised visual anomaly detection

Unsupervised anomaly detection on image data is notoriously unstable. We believe this is because many classical anomaly detectors implicitly assume data is low dimensional. However, image data is always high dimensional. Images can be projected to a low dimensional embedding but such projections rel...

Full description

Saved in:
Bibliographic Details
Main Authors: LIN, Wen-yan, LIU, Zhonghang, LIU, Siying
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2022
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7310
https://ink.library.smu.edu.sg/context/sis_research/article/8313/viewcontent/1673.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-8313
record_format dspace
spelling sg-smu-ink.sis_research-83132023-08-07T03:13:32Z Locally varying distance transform for unsupervised visual anomaly detection LIN, Wen-yan LIU, Zhonghang LIU, Siying Unsupervised anomaly detection on image data is notoriously unstable. We believe this is because many classical anomaly detectors implicitly assume data is low dimensional. However, image data is always high dimensional. Images can be projected to a low dimensional embedding but such projections rely on global transformations that truncate minor variations. As anomalies are rare, the final embedding often lacks the key variations needed to distinguish anomalies from normal instances. This paper proposes a new embedding using a set of locally varying data projections, with each projection responsible for persevering the variations that distinguish a local cluster of instances from all other instances. The locally varying embedding ensures the variations that distinguish anomalies are preserved, while simultaneously allowing the probability that an instance belongs to a cluster, to be statistically inferred from the one-dimensional, local projection associated with the cluster. Statistical agglomeration of an instance’s cluster membership probabilities, creates a global measure of its affinity to the dataset and causes anomalies to emerge, as instances whose affinity scores are surprisingly low. 2022-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7310 info:doi/10.1007/978-3-031-20056-4_21 https://ink.library.smu.edu.sg/context/sis_research/article/8313/viewcontent/1673.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University anomaly detection unsupervised high dimensions Bayesian Databases and Information Systems Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic anomaly detection
unsupervised
high dimensions
Bayesian
Databases and Information Systems
Graphics and Human Computer Interfaces
spellingShingle anomaly detection
unsupervised
high dimensions
Bayesian
Databases and Information Systems
Graphics and Human Computer Interfaces
LIN, Wen-yan
LIU, Zhonghang
LIU, Siying
Locally varying distance transform for unsupervised visual anomaly detection
description Unsupervised anomaly detection on image data is notoriously unstable. We believe this is because many classical anomaly detectors implicitly assume data is low dimensional. However, image data is always high dimensional. Images can be projected to a low dimensional embedding but such projections rely on global transformations that truncate minor variations. As anomalies are rare, the final embedding often lacks the key variations needed to distinguish anomalies from normal instances. This paper proposes a new embedding using a set of locally varying data projections, with each projection responsible for persevering the variations that distinguish a local cluster of instances from all other instances. The locally varying embedding ensures the variations that distinguish anomalies are preserved, while simultaneously allowing the probability that an instance belongs to a cluster, to be statistically inferred from the one-dimensional, local projection associated with the cluster. Statistical agglomeration of an instance’s cluster membership probabilities, creates a global measure of its affinity to the dataset and causes anomalies to emerge, as instances whose affinity scores are surprisingly low.
format text
author LIN, Wen-yan
LIU, Zhonghang
LIU, Siying
author_facet LIN, Wen-yan
LIU, Zhonghang
LIU, Siying
author_sort LIN, Wen-yan
title Locally varying distance transform for unsupervised visual anomaly detection
title_short Locally varying distance transform for unsupervised visual anomaly detection
title_full Locally varying distance transform for unsupervised visual anomaly detection
title_fullStr Locally varying distance transform for unsupervised visual anomaly detection
title_full_unstemmed Locally varying distance transform for unsupervised visual anomaly detection
title_sort locally varying distance transform for unsupervised visual anomaly detection
publisher Institutional Knowledge at Singapore Management University
publishDate 2022
url https://ink.library.smu.edu.sg/sis_research/7310
https://ink.library.smu.edu.sg/context/sis_research/article/8313/viewcontent/1673.pdf
_version_ 1773551432922824704