Saved in:
Bibliographic Details
Main Authors: Ma, Dabiao, Su, Zhiba, Yang, Jian, Fei, Haojun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.15867
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908781586153472
author Ma, Dabiao
Su, Zhiba
Yang, Jian
Fei, Haojun
author_facet Ma, Dabiao
Su, Zhiba
Yang, Jian
Fei, Haojun
contents This paper introduces a novel approach to securing machine learning model deployments against potential distribution shifts in practical applications, the Total Variation Out-of-Distribution (TV-OOD) detection method. Existing methods have produced satisfactory results, but TV-OOD improves upon these by leveraging the Total Variation Network Estimator to calculate each input's contribution to the overall total variation. By defining this as the total variation score, TV-OOD discriminates between in- and out-of-distribution data. The method's efficacy was tested across a range of models and datasets, consistently yielding results in image classification tasks that were either comparable or superior to those achieved by leading-edge out-of-distribution detection techniques across all evaluation metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15867
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Out-of-Distribution Detection Based on Total Variation Estimation
Ma, Dabiao
Su, Zhiba
Yang, Jian
Fei, Haojun
Computer Vision and Pattern Recognition
This paper introduces a novel approach to securing machine learning model deployments against potential distribution shifts in practical applications, the Total Variation Out-of-Distribution (TV-OOD) detection method. Existing methods have produced satisfactory results, but TV-OOD improves upon these by leveraging the Total Variation Network Estimator to calculate each input's contribution to the overall total variation. By defining this as the total variation score, TV-OOD discriminates between in- and out-of-distribution data. The method's efficacy was tested across a range of models and datasets, consistently yielding results in image classification tasks that were either comparable or superior to those achieved by leading-edge out-of-distribution detection techniques across all evaluation metrics.
title Out-of-Distribution Detection Based on Total Variation Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.15867