On the Detection of Anomalous or Out-Of-Distribution Data in Vision Models Using Statistical Techniques

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: O'Mahony, Laura, O'Sullivan, David JP, Nikolov, Nikola S.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916173149372416
author O'Mahony, Laura
O'Sullivan, David JP
Nikolov, Nikola S.
author_facet O'Mahony, Laura
O'Sullivan, David JP
Nikolov, Nikola S.
contents Out-of-distribution data and anomalous inputs are vulnerabilities of machine learning systems today, often causing systems to make incorrect predictions. The diverse range of data on which these models are used makes detecting atypical inputs a difficult and important task. We assess a tool, Benford's law, as a method used to quantify the difference between real and corrupted inputs. We believe that in many settings, it could function as a filter for anomalous data points and for signalling out-of-distribution data. We hope to open a discussion on these applications and further areas where this technique is underexplored.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15497
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the Detection of Anomalous or Out-Of-Distribution Data in Vision Models Using Statistical Techniques
O'Mahony, Laura
O'Sullivan, David JP
Nikolov, Nikola S.
Computer Vision and Pattern Recognition
Machine Learning
Out-of-distribution data and anomalous inputs are vulnerabilities of machine learning systems today, often causing systems to make incorrect predictions. The diverse range of data on which these models are used makes detecting atypical inputs a difficult and important task. We assess a tool, Benford's law, as a method used to quantify the difference between real and corrupted inputs. We believe that in many settings, it could function as a filter for anomalous data points and for signalling out-of-distribution data. We hope to open a discussion on these applications and further areas where this technique is underexplored.
title On the Detection of Anomalous or Out-Of-Distribution Data in Vision Models Using Statistical Techniques
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2403.15497