Communication Dans Un Congrès Année : 2021

Semi-Supervised Class Incremental Learning

Résumé

This paper makes a contribution to the problem of incremental class learning, the principle of which is to sequentially introduce batches of samples annotated with new classes during the learning phase. The main objective is to reduce the drop in classification performance on old classes, a phenomenon commonly called catastrophic forgetting. We propose in this paper a new method which exploits the availability of a large quantity of non-annotated images in addition to the annotated batches. These images are used to regularize the classifier and give the feature space a more stable structure. We demonstrate on two image data sets, MNIST and STL-10, that our approach is able to improve the global performance of classifiers learned using an incremental learning protocol, even with annotated batches of small size.

Fichier principal
Vignette du fichier
DTIS21025.1612433851.pdf (411.64 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03134825 , version 1 (08-02-2021)

Licence

Identifiants

Citer

Alexis Lechat, Stéphane Herbin, Frédéric Jurie. Semi-Supervised Class Incremental Learning. ICPR 2020, Jan 2021, Milan, Italy. pp.10383-10389, ⟨10.1109/ICPR48806.2021.9413225⟩. ⟨hal-03134825⟩
278 Consultations
618 Téléchargements

Altmetric

Partager

  • More