Coherence-based Sample Selection for Class-incremental Learning
Andrea Daou, Jean‐Baptiste Pothin, Paul Honeiné, Abdelaziz Bensrhair · 2025
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.