Generative Adversarial Stacked Autoencoders

TL;DR

This paper introduces GASCA, a new generative model combining adversarial training with stacked autoencoders, improving training efficiency and image quality over traditional GANs.

Contribution

It proposes a novel GASCA model and a gradual greedy layer-wise training algorithm for adversarial autoencoders, enhancing training stability and image reconstruction.

Findings

Lower reconstruction error compared to vanilla training

More stable training process

Improved image quality in generated samples

Abstract

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.