NECO: NEural Collapse Based Out-of-distribution detection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ammar, Mouïn Ben, Belkhir, Nacim, Popescu, Sebastian, Manzanera, Antoine, Franchi, Gianni
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917598774427648
author Ammar, Mouïn Ben
Belkhir, Nacim
Popescu, Sebastian
Manzanera, Antoine
Franchi, Gianni
author_facet Ammar, Mouïn Ben
Belkhir, Nacim
Popescu, Sebastian
Manzanera, Antoine
Franchi, Gianni
contents Detecting out-of-distribution (OOD) data is a critical challenge in machine learning due to model overconfidence, often without awareness of their epistemological limits. We hypothesize that ``neural collapse'', a phenomenon affecting in-distribution data for models trained beyond loss convergence, also influences OOD data. To benefit from this interplay, we introduce NECO, a novel post-hoc method for OOD detection, which leverages the geometric properties of ``neural collapse'' and of principal component spaces to identify OOD data. Our extensive experiments demonstrate that NECO achieves state-of-the-art results on both small and large-scale OOD detection tasks while exhibiting strong generalization capabilities across different network architectures. Furthermore, we provide a theoretical explanation for the effectiveness of our method in OOD detection. Code is available at https://gitlab.com/drti/neco
format Preprint
id arxiv_https___arxiv_org_abs_2310_06823
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle NECO: NEural Collapse Based Out-of-distribution detection
Ammar, Mouïn Ben
Belkhir, Nacim
Popescu, Sebastian
Manzanera, Antoine
Franchi, Gianni
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Detecting out-of-distribution (OOD) data is a critical challenge in machine learning due to model overconfidence, often without awareness of their epistemological limits. We hypothesize that ``neural collapse'', a phenomenon affecting in-distribution data for models trained beyond loss convergence, also influences OOD data. To benefit from this interplay, we introduce NECO, a novel post-hoc method for OOD detection, which leverages the geometric properties of ``neural collapse'' and of principal component spaces to identify OOD data. Our extensive experiments demonstrate that NECO achieves state-of-the-art results on both small and large-scale OOD detection tasks while exhibiting strong generalization capabilities across different network architectures. Furthermore, we provide a theoretical explanation for the effectiveness of our method in OOD detection. Code is available at https://gitlab.com/drti/neco
title NECO: NEural Collapse Based Out-of-distribution detection
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2310.06823