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.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |
