Fostering Diversity in Spatial Evolutionary Generative Adversarial Networks
Not on the map. Why?
Abstract (arXiv)
Generative adversary networks (GANs) suffer from training pathologies such as instability and mode collapse, which mainly arise from a lack of diversity in their adversarial interactions. Co-evolutionary GAN (CoE-GAN) training algorithms have shown to be resilient to these pathologies. This article introduces Mustangs, a spatially distributed CoE-GAN, which fosters diversity by using different loss functions during the training. Experimental analysis on MNIST and CelebA demonstrated that Mustangs trains statistically more accurate generators.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 11 references that are in the map. First posted on arXiv 25 Jun 2021.
Builds on
10 of 11 references.
References · 10
- 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 208
- 2016Learning What and Where to Drawcited by 105
- 2017Dual Motion GAN for Future-Flow Embedded Video Predictioncited by 69
- 2018Evolutionary Generative Adversarial Networkscited by 42
- 2017Triangle Generative Adversarial Networkscited by 12
- 2019Spatial Evolutionary Generative Adversarial Networkscited by 10
- 2018Towards Distributed Coevolutionary GANscited by 5
- 2020Data Dieting in GAN Trainingcited by 4
- 2018Lipizzaner: A System That Scales Robust Generative Adversarial Network Trainingcited by 3
- 2020Analyzing the Components of Distributed Coevolutionary GAN Trainingcited by 2
Built on by
Not cited yet.