Search Results for author: Victor Costa

Found 6 papers, 3 papers with code

Exploring Generative Adversarial Networks for Text-to-Image Generation with Evolution Strategies

1 code implementation6 Jul 2022 Victor Costa, Nuno Lourenço, João Correia, Penousal Machado

In this work, we follow a different direction by proposing the use of Covariance Matrix Adaptation Evolution Strategy to explore the latent space of Generative Adversarial Networks.

Text-to-Image Generation

Demonstrating the Evolution of GANs through t-SNE

no code implementations31 Jan 2021 Victor Costa, Nuno Lourenço, João Correia, Penousal Machado

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.

Evolutionary Algorithms

Exploring the Evolution of GANs through Quality Diversity

1 code implementation13 Jul 2020 Victor Costa, Nuno Lourenço, João Correia, Penousal Machado

We compare our proposal with the original COEGAN model and with an alternative version using a global competition approach.

Evolutionary Algorithms

Using Skill Rating as Fitness on the Evolution of GANs

no code implementations9 Apr 2020 Victor Costa, Nuno Lourenço, João Correia, Penousal Machado

Recent works proposed the use of evolutionary algorithms on GAN training, aiming to solve these challenges and to provide an automatic way to find good models.

Evolutionary Algorithms

Coevolution of Generative Adversarial Networks

no code implementations12 Dec 2019 Victor Costa, Nuno Lourenço, Penousal Machado

Therefore, this project proposes COEGAN, a model that combines neuroevolution and coevolution in the coordination of the GAN training algorithm.

COEGAN: Evaluating the Coevolution Effect in Generative Adversarial Networks

1 code implementation12 Dec 2019 Victor Costa, Nuno Lourenço, João Correia, Penousal Machado

COEGAN is a model that uses neuroevolution and coevolution in the GAN training algorithm to provide a more stable training method and the automatic design of neural network architectures.

Cannot find the paper you are looking for? You can Submit a new open access paper.