Spatial evolutionary generative adversarial networks

Toutouh, Jamal; Hemberg, Erik; O’Reilly, Una-May

doi:10.1145/3321707.3321860

Cited by 47 publications

(37 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Progress was made in both the resulting quality of the outcome and the stability of the GAN training. Methods such as E-GAN [31], Pareto GAN [11], Lipizzaner [1], Mustangs [30], and COEGAN [7,9] use different approaches to apply Evolutionary Algorithms on the training of GANs.…”

Section: Introductionmentioning

confidence: 99%

Demonstrating the Evolution of GANs Through t-SNE

Costa¹,

Lourenço²,

Correia³

et al. 2021

Applications of Evolutionary Computation

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) are powerful generative models that achieved strong results, mainly in the image domain. However, the training of GANs is not trivial, presenting some challenges tackled by different strategies. Evolutionary algorithms, such as COEGAN, were recently proposed as a solution to improve the GAN training, overcoming common problems that affect the model, such as vanishing gradient and mode collapse. In this work, we propose an evaluation method based on t-distributed Stochastic Neighbour Embedding (t-SNE) to assess the progress of GANs and visualize the distribution learned by generators in training. We propose the use of the feature space extracted from trained discriminators to evaluate samples produced by generators and from the input dataset. A metric based on the resulting t-SNE maps and the Jaccard index is proposed to represent the model quality. Experiments were conducted to assess the progress of GANs when trained using COEGAN. The results show both by visual inspection and metrics that the Evolutionary Algorithm gradually improves discriminators and generators through generations, avoiding problems such as mode collapse.

show abstract

Section: Introductionmentioning

confidence: 99%

Demonstrating the Evolution of GANs Through t-SNE

Costa¹,

Lourenço²,

Correia³

et al. 2021

Applications of Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…The proposed approach applies the methodology introduced by Lipizzaner [15] and Mustangs [19]. A distributed GAN training is performed by applying coevolutionary algorithms (coEA).…”

Section: Distributed Gan Trainingmentioning

confidence: 99%

Parallel/Distributed Generative Adversarial Neural Networks for Data Augmentation of COVID-19 Training Images

Toutouh

Esteban

Nesmachnow

2021

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

This article presents an approach using parallel/distributed generative adversarial networks for image data augmentation, applied to generate COVID-19 training samples for computational intelligence methods. This is a relevant problem nowadays, considering the recent COVID-19 pandemic. Computational intelligence and learning methods are useful tools to assist physicians in the process of diagnosing diseases and acquire valuable medical knowledge. A specific generative adversarial network approach trained using a co-evolutionary algorithm is implemented, including a three-level parallel approach combining distributed memory and fine-grained parallelization using CPU and GPU. The experimental evaluation of the proposed method was performed on the high performance computing infrastructure provided by National Supercomputing Center, Uruguay. The main experimental results indicate that the proposed model is able to generate accurate images and the 3 × 3 version of the distributed GAN has better robustness properties of its training process, allowing to generate better and more diverse images.

show abstract

“…This metric is capable of quantifying the quality and diversity of the generative model. The use of evolutionary algorithms to train and evolve GANs was recently proposed [1,4,5,8,27,28]. The solutions present a diverse set of strategies to not only overcome common GAN problems but also to provide better quality on the produced samples.…”

Section: Background and Related Workmentioning

confidence: 99%

“…However, the networks of the discriminator and generator are fixed and only the internal parameters (e.g., weights) change through evolution. A further improvement over Lipizzaner, called Mustangs [27], applies the E-GAN dynamic loss function to the algorithm while keeping the same spatial coevolution strategy of Lipizzaner.…”

Section: Background and Related Workmentioning

confidence: 99%

“…Another strategy to improve the training of GANs is the application of evolutionary algorithms. In this context, recent solutions were designed to improve the training process and the quality of the outcome [1,4,5,8,27,28]. These proposals incorporate mechanisms such as neuroevolution, coevolution, and spatial coevolution, making use of evolutionary pressure to achieve efficient models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring the evolution of GANs through quality diversity

Costa

Lourenço

Correia

et al. 2020

Proceedings of the 2020 Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

Generative adversarial networks (GANs) achieved relevant advances in the field of generative algorithms, presenting high-quality results mainly in the context of images. However, GANs are hard to train, and several aspects of the model should be previously designed by hand to ensure training success. In this context, evolutionary algorithms such as COEGAN were proposed to solve the challenges in GAN training. Nevertheless, the lack of diversity and premature optimization can be found in some of these solutions. We propose in this paper the application of a quality-diversity algorithm in the evolution of GANs. The solution is based on the Novelty Search with Local Competition (NSLC) algorithm, adapting the concepts used in COEGAN to this new proposal. We compare our proposal with the original COEGAN model and with an alternative version using a global competition approach. The experimental results evidenced that our proposal increases the diversity of the discovered solutions and leverage the performance of the models found by the algorithm. Furthermore, the global competition approach was able to consistently find better models for GANs. CCS CONCEPTS • Computing methodologies → Genetic algorithms; Neural networks;

show abstract

Spatial evolutionary generative adversarial networks

Cited by 47 publications

References 18 publications

Demonstrating the Evolution of GANs Through t-SNE

Demonstrating the Evolution of GANs Through t-SNE

Parallel/Distributed Generative Adversarial Neural Networks for Data Augmentation of COVID-19 Training Images

Exploring the evolution of GANs through quality diversity

Contact Info

Product

Resources

About