Unsupervised Latent Regression through Information Maximization - Contrastive Regularized GAN

Page view(s)
13
Checked on Feb 08, 2025
Unsupervised Latent Regression through Information Maximization - Contrastive Regularized GAN
Title:
Unsupervised Latent Regression through Information Maximization - Contrastive Regularized GAN
Journal Title:
2024 IEEE Conference on Artificial Intelligence (CAI)
Publication Date:
30 July 2024
Citation:
Sintunata, V., Liu, S., Nguyen Van, D., Lim, Z. Y., Zhikuan, R. L., Wang, Y., Feng, J. H. J., & Leman, K. (2024, June 25). Unsupervised Latent Regression through Information Maximization - Contrastive Regularized GAN. 2024 IEEE Conference on Artificial Intelligence (CAI). https://doi.org/10.1109/cai59869.2024.00264
Abstract:
Most of labelled image public datasets are discrete in nature, e.g. cat vs dog, human, car, etc. With the growing complexity of tasks, fine-grained label data is needed. Fine-grained labels are costly because there is a need for experts to label them. Generative Adversarial Network (GAN) has been gaining a lot of attentions due to its ability to not only generate realistic images but also to disentangle the attributes of the images. Unfortunately, GAN’s disentanglement methods usually lack the ability to quantify such attributes. The objective of this work is to quantify the attributes of the target (object/image) based on the disentangled properties without supervision. In order to get the (disentangled) attributes, we leverage GAN with information maximization and contrastive regularizer. Regression is done by adding additional layer to the contrastive networks of the model. The regression quality of the proposed method is quantified by order quality measured using normalized Kendall’s Tau. Furthermore, an application in denoising image is also presented.
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done
Description:
© 2024 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.
ISBN:
979-8-3503-5409-6
Files uploaded:

File Size Format Action
gan-regression-ieeecai2024.pdf 7.14 MB PDF Request a copy