Dual-Domain Division Multiplexer for General Continual Learning : A Pseudo Causal Intervention Strategy

As a continual learning paradigm where non-stationary data arrive in the form of streams and training occurs whenever a small batch of samples is accumulated, general continual learning (GCL) suffers from both inter-task bias and intra-task bias. Existing GCL methods can hardly simultaneously handle...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 34(2025) vom: 02., Seite 1966-1979
1. Verfasser: Wu, Jialu (VerfasserIn)
Weitere Verfasser: Wang, Shaofan, Sun, Yanfeng, Yin, Baocai, Huang, Qingming
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article