Enregistré dans:
Détails bibliographiques
Auteurs principaux: Mussard, Romain, Pacheco, Fannia, Berar, Maxime, Gasso, Gilles, Honeine, Paul
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.17899
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915904692944896
author Mussard, Romain
Pacheco, Fannia
Berar, Maxime
Gasso, Gilles
Honeine, Paul
author_facet Mussard, Romain
Pacheco, Fannia
Berar, Maxime
Gasso, Gilles
Honeine, Paul
contents Deep learning models have significantly improved the ability to detect novelties in time series (TS) data. This success is attributed to their strong representation capabilities. However, due to the inherent variability in TS data, these models often struggle with generalization and robustness. To address this, a common approach is to perform Unsupervised Domain Adaptation, particularly Universal Domain Adaptation (UniDA), to handle domain shifts and emerging novel classes. While extensively studied in computer vision, UniDA remains underexplored for TS data. This work provides a comprehensive implementation and comparison of state-of-the-art TS backbones in a UniDA framework. We propose a reliable protocol to evaluate their robustness and generalization across different domains. The goal is to provide practitioners with a framework that can be easily extended to incorporate future advancements in UniDA and TS architectures. Our results highlight the critical influence of backbone selection in UniDA performance and enable a robustness analysis across various datasets and architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17899
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Universal Domain Adaptation Benchmark for Time Series Data Representation
Mussard, Romain
Pacheco, Fannia
Berar, Maxime
Gasso, Gilles
Honeine, Paul
Machine Learning
Deep learning models have significantly improved the ability to detect novelties in time series (TS) data. This success is attributed to their strong representation capabilities. However, due to the inherent variability in TS data, these models often struggle with generalization and robustness. To address this, a common approach is to perform Unsupervised Domain Adaptation, particularly Universal Domain Adaptation (UniDA), to handle domain shifts and emerging novel classes. While extensively studied in computer vision, UniDA remains underexplored for TS data. This work provides a comprehensive implementation and comparison of state-of-the-art TS backbones in a UniDA framework. We propose a reliable protocol to evaluate their robustness and generalization across different domains. The goal is to provide practitioners with a framework that can be easily extended to incorporate future advancements in UniDA and TS architectures. Our results highlight the critical influence of backbone selection in UniDA performance and enable a robustness analysis across various datasets and architectures.
title Universal Domain Adaptation Benchmark for Time Series Data Representation
topic Machine Learning
url https://arxiv.org/abs/2505.17899