Pairwise Augmented GANs with Adversarial Reconstruction Loss
This work addresses image generation and reconstruction for computer vision applications, but it is incremental as it builds on existing GAN and autoencoder frameworks.
The paper tackles the problem of generating realistic samples and reconstructions in autoencoding models by proposing Pairwise Augmented GANs with an adversarial reconstruction loss, achieving competitive quality on MNIST, CIFAR10, and CelebA datasets and good quantitative results on CIFAR10.
We propose a novel autoencoding model called Pairwise Augmented GANs. We train a generator and an encoder jointly and in an adversarial manner. The generator network learns to sample realistic objects. In turn, the encoder network at the same time is trained to map the true data distribution to the prior in latent space. To ensure good reconstructions, we introduce an augmented adversarial reconstruction loss. Here we train a discriminator to distinguish two types of pairs: an object with its augmentation and the one with its reconstruction. We show that such adversarial loss compares objects based on the content rather than on the exact match. We experimentally demonstrate that our model generates samples and reconstructions of quality competitive with state-of-the-art on datasets MNIST, CIFAR10, CelebA and achieves good quantitative results on CIFAR10.