no code implementations • 12 Mar 2024 • Eduard Hogea, Adrian Popescu, Darian Onchis, Grégoire Petit
Exemplar-free class-incremental learning (EFCIL) poses significant challenges, primarily due to catastrophic forgetting, necessitating a delicate balance between stability and plasticity to accurately recognize both new and previous classes.
no code implementations • 22 Aug 2023 • Grégoire Petit, Michael Soumm, Eva Feillet, Adrian Popescu, Bertrand Delezoide, David Picard, Céline Hudelot
Our main finding is that the initial training strategy is the dominant factor influencing the average incremental accuracy, but that the choice of CIL algorithm is more important in preventing forgetting.
2 code implementations • 23 Nov 2022 • Grégoire Petit, Adrian Popescu, Hugo Schindler, David Picard, Bertrand Delezoide
Actual features of new classes and pseudo-features of past classes are fed into a linear classifier which is trained incrementally to discriminate between all classes.
no code implementations • 14 Sep 2022 • Grégoire Petit, Adrian Popescu, Eden Belouadah, David Picard, Bertrand Delezoide
Mainstream methods need to store two deep models since they integrate new classes using fine-tuning with knowledge distillation from the previous incremental state.