Abstract
We propose in this paper a new approach to train the Generative Adversarial Nets (GANs) with a mixture of generators to overcome the mode collapsing problem. The main intuition is to employ multiple generators, instead of using a single one as in the original GAN. The idea is simple, yet proven to be extremely effective at covering diverse data modes, easily overcoming the mode collapsing problem and delivering state-of-the-art results. A minimax formulation was able to establish among a classifier, a discriminator, and a set of generators in a similar spirit with GAN. Generators create samples that are intended to come from the same distribution as the training data, whilst the discriminator determines whether samples are true data or generated by generators, and the classifier specifies which generator a sample comes from. The distinguishing feature is that internal samples are created from multiple generators, and then one of them will be randomly selected as final output similar to the mechanism of a probabilistic mixture model. We term our method Mixture Generative Adversarial Nets (MGAN). We develop theoretical analysis to prove that, at the equilibrium, the Jensen-Shannon divergence (JSD) between the mixture of generators’ distributions and the empirical data distribution is minimal, whilst the JSD among generators’ distributions is maximal, hence effectively avoiding the mode collapsing problem. By utilizing parameter sharing, our proposed model adds minimal computational cost to the standard GAN, and thus can also efficiently scale to large-scale datasets. We conduct extensive experiments on synthetic 2D data and natural image databases (CIFAR-10, STL-10 and ImageNet) to demonstrate the superior performance of our MGAN in achieving state-of-the-art Inception scores over latest baselines, generating diverse and appealing recognizable objects at different resolutions, and specializing in capturing different types of objects by the generators.
| Original language | English |
|---|---|
| Title of host publication | 6th International Conference on Learning Representations, ICLR 2018 |
| Editors | Iain Murray, Marc’Aurelio Ranzato, Oriol Vinyals |
| Place of Publication | Amherst MA USA |
| Publisher | OpenReview |
| Number of pages | 24 |
| Publication status | Published - 2018 |
| Externally published | Yes |
| Event | International Conference on Learning Representations 2018 - Vancouver, Canada Duration: 30 Apr 2018 → 3 May 2018 Conference number: 6th https://iclr.cc/Conferences/2018 https://openreview.net/group?id=ICLR.cc/2018/Conference (Proceedings) |
Conference
| Conference | International Conference on Learning Representations 2018 |
|---|---|
| Abbreviated title | ICLR 2018 |
| Country/Territory | Canada |
| City | Vancouver |
| Period | 30/04/18 → 3/05/18 |
| Internet address |
Keywords
- GANs
- Mode Collapse
- Mixture
- Jensen-Shannon Divergence
- Inception Score
- Generator
- Discriminator
- CIFAR-10
- STL-10
- ImageNet
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver