Saved in:
Bibliographic Details
Main Authors: Dadalto, Eduardo, Alberge, Florence, Duhamel, Pierre, Piantanida, Pablo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.16045
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916298624073728
author Dadalto, Eduardo
Alberge, Florence
Duhamel, Pierre
Piantanida, Pablo
author_facet Dadalto, Eduardo
Alberge, Florence
Duhamel, Pierre
Piantanida, Pablo
contents This paper introduces a universal approach to seamlessly combine out-of-distribution (OOD) detection scores. These scores encompass a wide range of techniques that leverage the self-confidence of deep learning models and the anomalous behavior of features in the latent space. Not surprisingly, combining such a varied population using simple statistics proves inadequate. To overcome this challenge, we propose a quantile normalization to map these scores into p-values, effectively framing the problem into a multi-variate hypothesis test. Then, we combine these tests using established meta-analysis tools, resulting in a more effective detector with consolidated decision boundaries. Furthermore, we create a probabilistic interpretable criterion by mapping the final statistics into a distribution with known parameters. Through empirical investigation, we explore different types of shifts, each exerting varying degrees of impact on data. Our results demonstrate that our approach significantly improves overall robustness and performance across diverse OOD detection scenarios. Notably, our framework is easily extensible for future developments in detection scores and stands as the first to combine decision boundaries in this context. The code and artifacts associated with this work are publicly available\footnote{\url{https://github.com/edadaltocg/detectors}}.
format Preprint
id arxiv_https___arxiv_org_abs_2406_16045
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Combine and Conquer: A Meta-Analysis on Data Shift and Out-of-Distribution Detection
Dadalto, Eduardo
Alberge, Florence
Duhamel, Pierre
Piantanida, Pablo
Machine Learning
Artificial Intelligence
This paper introduces a universal approach to seamlessly combine out-of-distribution (OOD) detection scores. These scores encompass a wide range of techniques that leverage the self-confidence of deep learning models and the anomalous behavior of features in the latent space. Not surprisingly, combining such a varied population using simple statistics proves inadequate. To overcome this challenge, we propose a quantile normalization to map these scores into p-values, effectively framing the problem into a multi-variate hypothesis test. Then, we combine these tests using established meta-analysis tools, resulting in a more effective detector with consolidated decision boundaries. Furthermore, we create a probabilistic interpretable criterion by mapping the final statistics into a distribution with known parameters. Through empirical investigation, we explore different types of shifts, each exerting varying degrees of impact on data. Our results demonstrate that our approach significantly improves overall robustness and performance across diverse OOD detection scenarios. Notably, our framework is easily extensible for future developments in detection scores and stands as the first to combine decision boundaries in this context. The code and artifacts associated with this work are publicly available\footnote{\url{https://github.com/edadaltocg/detectors}}.
title Combine and Conquer: A Meta-Analysis on Data Shift and Out-of-Distribution Detection
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.16045