Ye, Fei and Bors, Adrian Gheorghe orcid.org/0000-0001-7838-0021 (2022) Continual Variational Autoencoder Learning via Online Cooperative Memorization. In: Proceedings of the European Conference on Computer Vision (ECCV). Lecture Notes in Computer Science (LNCS) . Springer , 531–549.
Abstract
Due to their inference, data representation and reconstruction properties, Variational Autoencoders (VAE) have been successfully used in continual learning classification tasks. However, their ability to generate images with specifications corresponding to the classes and databases learned during Continual Learning (CL) is not well understood and catastrophic forgetting remains a significant challenge. In this paper, we firstly analyze the forgetting behaviour of VAEs by developing a new theoretical framework that formulates CL as a dynamic optimal transport problem. This framework proves approximate bounds to the data likelihood without requiring the task information and explains how the prior knowledge is lost during the training process. We then propose a novel memory buffering approach, namely the Online Cooperative Memorization (OCM) framework, which consists of a Short-Term Memory (STM) that continually stores recent samples to provide future information for the model, and a Long-Term Memory (LTM) aiming to preserve a wide diversity of samples. The proposed OCM transfers certain samples from STM to LTM according to the information diversity selection criterion without requiring any supervised signals. The OCM framework is then combined with a dynamic VAE expansion mixture network for further enhancing its performance.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Depositing User: | Pure (York) |
Date Deposited: | 12 Aug 2022 11:50 |
Last Modified: | 18 Dec 2024 00:40 |
Published Version: | https://doi.org/10.1007/978-3-031-20050-2_31 |
Status: | Published |
Publisher: | Springer |
Series Name: | Lecture Notes in Computer Science (LNCS) |
Identification Number: | 10.1007/978-3-031-20050-2_31 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:189727 |
Download
Filename: OnlineCooperativeMemory_ECCV2022.pdf
Description: OnlineCooperativeMemory_ECCV2022