First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning

no code implementations • ICCV 2023 • Aristeidis Panos, Yuriko Kobe, Daniel Olmeda Reino, Rahaf Aljundi, Richard E. Turner

In this work, we develop a baseline method, First Session Adaptation (FSA), that sheds light on the efficacy of existing CIL approaches and allows us to assess the relative performance contributions from head and body adaption.

Class Incremental Learning Image Classification +1