Online Class Incremental Learning with One-Vs-All Classifiers for Resource Constrained Devices

Online Class Incremental Learning (OCIL) aims to learn new classes from a data stream where samples arrive in batches, one after the other. Avoiding catastrophic forgetting, the phenomenon of forgetting old classes when learning new ones is the main challenge in OCIL. Replay-based methods counteract...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2023 International Symposium on Image and Signal Processing and Analysis (ISPA) S. 1 - 6
Hauptverfasser:	Baptiste, Wagner, Denis, Pellerin, Serge, Olympieff, Sylvain, Huet
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 18.09.2023
Schlagworte:	Benchmark testing Catas-trophic forgetting Computational modeling Incremental learning Online learning Real-time systems Replay Signal processing Stability analysis Streaming media Training
ISSN:	1849-2266
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!