Ye, Fei and Bors, Adrian Gheorghe orcid.org/0000-0001-7838-0021 (2024) Self-Supervised Adversarial Variational Learning. Pattern Recognition. 110156. ISSN 0031-3203
Abstract
A natural approach for representation learning is to combine the inference mechanisms of VAEs and the generation capabilities of GANs, within a new model, namely VAEGAN. Most existing VAEGAN models would jointly train the generator and inference modules, which has limitations when learning representations generated by a pre-trained GAN model without data. In this paper, we develop a novel hybrid model, called the Self-Supervised Adversarial Variational Learning (SS-AVL) which introduces a two-step optimization procedure training separately the generator and the inference model. The primary advantage of SS-AVL over existing VAEGAN models is that SS-AVL optimizes the inference models in a self-supervised learning manner where the samples used for training the inference models are drawn from the generator distribution instead of using real samples. This can allow SS-AVL to learn representations from arbitrary GAN models without using real data. Additionally, we employ information maximization into the context of increasing the maximum likelihood, which encourages SS-AVL to learn meaningful latent representations. We perform extensive experiments to demonstrate the effectiveness of the proposed SS-AVL model.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2023 The Authors. |
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: | 21 Dec 2024 00:26 |
Last Modified: | 21 Dec 2024 00:26 |
Published Version: | https://doi.org/10.1016/j.patcog.2023.110156 |
Status: | Published |
Refereed: | Yes |
Identification Number: | 10.1016/j.patcog.2023.110156 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:221041 |
Download
Filename: 1-s2.0-S0031320323008531-main.pdf
Description: Self-Supervised Adversarial Variational Learning
Licence: CC-BY 2.5