Unsupervised Generative Variational Continual Learning

Unsupervised Generative Variational Continual Learning

2022 IEEE International Conference on Image Processing (ICIP)

10.1109/ICIP46576.2022.9897538

http://dx.doi.org/10.1109/icip46576.2022.9897538

Liu Guimeng, Guo Yang, Cheryl Wong Sze Yin, Ponnuthurai Nagartnam Suganathan, Ramasamy Savitha

03 November 2022

Guimeng, L., Yang, G., Sze Yin, C. W., Nagartnam Suganathan, P., & Savitha, R. (2022). Unsupervised Generative Variational Continual Learning. 2022 IEEE International Conference on Image Processing (ICIP). https://doi.org/10.1109/icip46576.2022.9897538

Continual learning aims at learning a sequence of tasks with- out forgetting any task. While most of the existing literature in continual learning is aimed at class incremental learning in a supervised setting, there is an enormous potential for unsu- pervised continual learning using generative models. This pa- per proposes a combination of architectural pruning and neu- ron addition in generative variational models toward unsuper- vised generative continual learning (UGCL). Evaluations on standard benchmark data sets demonstrate the superior gener- ative ability of the proposed method

Publisher Copyright

This research / project is supported by the National Research Foundation - AI Singapore Programme
Grant Reference no. : AISG2-RP-2021-027

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/19210

2381-8549

Institute for Infocomm Research