It takes (only) two: adversarial generator-encoder networks

Conference item

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.

Authors: Ulyanov, D; Vedaldi, A; Lempitsky, V

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Association for the Advancement of Artificial Intelligence
• Host title: Association for the Advancement of Artificial Intelligence (AAAI), 2018: Thirty Second AAAAI Conference on Artificial Intelligence, New Orleans, Louisiana USA — February 2–7, 2018
• Journal: Association for the Advancement of Artificial Intelligence (AAAI), 2018
• Pages: 1250-1257
• Publication date: 2018-04-25
• Acceptance date: 2017-11-08
• EISSN: 2374-3468
• ISBN: 9781577358008