Adversarial Code Learning for Image Generation
This addresses the need for more flexible and high-performing generative models in machine learning, though it appears incremental as it builds on existing GAN and autoencoder frameworks.
The paper tackles the problem of improving image generation performance by introducing an adversarial code learning (ACL) module that shifts learning from pixel spaces to latent code spaces, achieving significant improvements on datasets like MNIST, CIFAR-10, and CelebA.
We introduce the "adversarial code learning" (ACL) module that improves overall image generation performance to several types of deep models. Instead of performing a posterior distribution modeling in the pixel spaces of generators, ACLs aim to jointly learn a latent code with another image encoder/inference net, with a prior noise as its input. We conduct the learning in an adversarial learning process, which bears a close resemblance to the original GAN but again shifts the learning from image spaces to prior and latent code spaces. ACL is a portable module that brings up much more flexibility and possibilities in generative model designs. First, it allows flexibility to convert non-generative models like Autoencoders and standard classification models to decent generative models. Second, it enhances existing GANs' performance by generating meaningful codes and images from any part of the prior. We have incorporated our ACL module with the aforementioned frameworks and have performed experiments on synthetic, MNIST, CIFAR-10, and CelebA datasets. Our models have achieved significant improvements which demonstrated the generality for image generation tasks.