%0 Conference Proceedings
%T Looking Through the Past: Better Knowledge Retention for Generative Replay in Continual Learning
%A Valeriya Khan
%A Sebastian Cygert
%A Bartlomiej Twardowski
%A Tomasz Trzcinski
%B Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops
%D 2023
%F Valeriya Khan2023
%O LAMP
%O exported from refbase (http://158.109.8.37/show.php?record=3942), last updated on Tue, 06 Feb 2024 12:15:52 +0100
%X In this work, we improve the generative replay in a continual learning setting. We notice that in VAE-based generative replay, the generated features are quite far from the original ones when mapped to the latent space. Therefore, we propose modifications that allow the model to learn and generate complex data. More specifically, we incorporate the distillation in latent space between the current and previous models to reduce feature drift. Additionally, a latent matching for the reconstruction and original data is proposed to improve generated features alignment. Further, based on the observation that the reconstructions are better for preserving knowledge, we add the cycling of generations through the previously trained model to make them closer to the original data. Our method outperforms other generative replay methods in various scenarios.
%U https://openaccess.thecvf.com/content/ICCV2023W/VCL/html/Khan_Looking_Through_the_Past_Better_Knowledge_Retention_for_Generative_Replay_ICCVW_2023_paper.html
%U http://158.109.8.37/files/KCT2023.pdf
%P 3496-3500