Qin, Y;
Mitra, N;
Wonka, P;
(2020)
How Does Lipschitz Regularization Influence GAN Training?
In:
Computer Vision – ECCV 2020. ECCV 2020.
(pp. pp. 310-326).
Springer: Cham, Switzerland.
Preview |
Text
lipsc.pdf - Accepted Version Download (63MB) | Preview |
Abstract
Despite the success of Lipschitz regularization in stabilizing GAN training, the exact reason of its effectiveness remains poorly understood. The direct effect of K-Lipschitz regularization is to restrict the L2-norm of the neural network gradient to be smaller than a threshold K (e.g.,) such that. In this work, we uncover an even more important effect of Lipschitz regularization by examining its impact on the loss function: It degenerates GAN loss functions to almost linear ones by restricting their domain and interval of attainable gradient values. Our analysis shows that loss functions are only successful if they are degenerated to almost linear ones. We also show that loss functions perform poorly if they are not degenerated and that a wide range of functions can be used as loss function as long as they are sufficiently degenerated by regularization. Basically, Lipschitz regularization ensures that all loss functions effectively work in the same way. Empirically, we verify our proposition on the MNIST, CIFAR10 and CelebA datasets.
| Type: | Proceedings paper |
|---|---|
| Title: | How Does Lipschitz Regularization Influence GAN Training? |
| ISBN-13: | 9783030585167 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1007/978-3-030-58517-4_19 |
| Publisher version: | https://doi.org/10.1007/978-3-030-58517-4_19 |
| 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 Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10117239 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
