Generative Adversarial Networks (GANs) have become predominant in image generation tasks. Their success is attributed to the training regime which employs two models: a generator G and discriminator D that compete in a minimax zero sum game. Nonetheless, GANs are difficult to train due to their sensitivity to hyperparameter and parameter initialisation, which often leads to vanishing gradients, non-convergence, or mode collapse, where the generator is unable to create samples with different variations. In this work, we propose a novel Generative Adversarial Stacked Convolutional Autoencoder(GASCA) model and a generative adversarial gradual greedy layer-wise learning algorithm de-signed to train Adversarial Autoencoders in an efficient and incremental manner. Our training approach produces images with significantly lower reconstruction error than vanilla joint training.
@article{arxiv.2011.12236,
title = {Generative Adversarial Stacked Autoencoders},
author = {Ariel Ruiz-Garcia and Ibrahim Almakky and Vasile Palade and Luke Hicks},
journal= {arXiv preprint arXiv:2011.12236},
year = {2020}
}
Comments
arXiv admin note: text overlap with arXiv:2007.09790