Class-Prototype Conditional Diffusion Model for Continual Learning with Generative Replay

The paper proposes a Class-Prototype conditional Diffusion Model (CPDM) for continual learning with generative replay. The model uses a diffusion-based generator and a classifier to mitigate catastrophic forgetting in classifiers.

Data and Resources

Cite this as

Khanh Doan, Quyen Tran, Tuan Nguyen, Dinh Phung, Trung Le (2024). Dataset: Class-Prototype Conditional Diffusion Model for Continual Learning with Generative Replay. https://doi.org/10.57702/i1b1a1qi

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.2312.06710
Author Khanh Doan
More Authors
Quyen Tran
Tuan Nguyen
Dinh Phung
Trung Le
Homepage https://github.com/dnkhanh45/CPDM