Communication Dans Un Congrès Année : 2025

Coherence-based Sample Selection for Class-incremental Learning

Résumé

Class-Incremental Learning (Class-IL) is challenging as the model must adapt to new classes while retaining knowledge of old ones. To avoid catastrophic forgetting in knowledge distillation with a fixed-budget memory, exemplars from previously learned classes need to be stored. We propose a novel sample selection method based on the coherence measure to boost Class-IL performance. This is the first time the coherence is investigated in a deep model, specifically for Class-IL. We define the coherence between two samples as a normalized inner product between their deep feature extractor features. Theoretical results and extensive experiments demonstrate the relevance of our approach.

Fichier principal
Vignette du fichier
Esann_coherence.pdf (303.56 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04937562 , version 1 (10-02-2025)

Licence

Identifiants

  • HAL Id : hal-04937562 , version 1

Citer

Andrea Daou, Jean-Baptiste Pothin, Paul Honeine, Abdelaziz Bensrhair. Coherence-based Sample Selection for Class-incremental Learning. 33rd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Apr 2025, Bruges, Belgium. ⟨hal-04937562⟩
206 Consultations
166 Téléchargements

Partager

  • More