Xiao, Baoren;
Ni, Hao;
Yang, Weixin;
(2025)
MCGAN: Enhancing GAN Training with Regression-Based Generator Loss.
In:
Proceedings of the AAAI Conference on Artificial Intelligence.
(pp. pp. 21644-21652).
Association for the Advancement of Artificial Intelligence (AAAI): Philadelphia, PA, USA.
Preview |
Text
MCGAN_AAAI_CameraReady.pdf - Accepted Version Download (3MB) | Preview |
Abstract
Generative adversarial networks (GANs) have emerged as a powerful tool for generating high-fidelity data. However, the main bottleneck of existing approaches is the lack of supervision on the generator training, which often results in undamped oscillation and unsatisfactory performance. To address this issue, we propose an algorithm called Monte Carlo GAN (MCGAN). This approach, utilizing an innovative generative loss function, termed the regression loss, reformulates the generator training as a regression task and enables the generator training by minimizing the mean squared error between the discriminator's output of real data and the expected discriminator of fake data. We demonstrate the desirable analytic properties of the regression loss, including discriminability and optimality, and show that our method requires a weaker condition on the discriminator for effective generator training. These properties justify the strength of this approach to improve the training stability while retaining the optimality of GAN by leveraging strong supervision of the regression loss. Extensive experiments on diverse datasets, including image data (CIFAR-10/100, FFHQ256, ImageNet, and LSUN Bedroom), time series data (VAR and stock data), and video data, are conducted to demonstrate the flexibility and effectiveness of our proposed MCGAN. Numerical results show that the proposed MCGAN is versatile in enhancing a variety of backbone GAN models and achieves consistent and significant improvement in terms of quality, accuracy, training stability, and learned latent space.
| Type: | Proceedings paper |
|---|---|
| Title: | MCGAN: Enhancing GAN Training with Regression-Based Generator Loss |
| Event: | 39th Annual AAAI Conference on Artificial Intelligence |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1609/aaai.v39i20.35468 |
| Publisher version: | https://doi.org/10.1609/aaai.v39i20.35468 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Mathematics |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10207066 |
Archive Staff Only
 |
View Item |
