Communication Dans Un Congrès Année : 2025

Universal Domain Adaptation Benchmark for Time Series Data Representation

Romain Mussard
  • Fonction : Auteur
  • PersonId : 1531630
Fannia Pacheco
Maxime Berar
Gilles Gasso
Paul Honeine

Résumé

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.

Fichier principal
Vignette du fichier
UniDABench.pdf (530.83 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05082451 , version 1 (09-06-2025)

Licence

Identifiants

  • HAL Id : hal-05082451 , version 1

Citer

Romain Mussard, Fannia Pacheco, Maxime Berar, Gilles Gasso, Paul Honeine. Universal Domain Adaptation Benchmark for Time Series Data Representation. 33rd European Signal Processing Conference, Sep 2025, Palerme, Italy. ⟨hal-05082451⟩
153 Consultations
166 Téléchargements

Partager

  • More