Work

It Takes (Only) Two: Adversarial Generator-Encoder Networks

Year: 2018
Type: article
Abstract: We present a new autoencoder-type architecture that is trainable in an unsupervised mode, sustains both generation and inference, and has the quality of conditional and unconditional samples boosted by adversarial learning. Unlike previous hybrids of autoencoders and adversarial networks, the adversarial game in our approach is set up directly between the encoder and the generator, and no external mappings are trained in the process of learning.The game objective compares the divergences of each of the real and the generated data distributions with the prior distribution in the latent space. We show that direct generator-vs-encoder game leads to a tight coupling of the two components, resulting in samples and reconstructions of a comparable quality to some recently-proposed more complex architectures.
Language: English
Open Access status: green
OpenAlex ID: W2962706768
FWCI: 7.846
Cites: 28
Cited by: 122
Related to: 10