In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We explore models that are capable of combining the attributes of multiple inputs such that a resynthesised output is trained to fool an adversarial discriminator for real versus synthesised data. Furthermore, we explore the use of such an architecture in the context of semi-supervised learning, where we learn a mixing function whose objective is to produce interpolations of hidden states, or masked combinations of latent representations that are consistent with a conditioned class label. We show quantitative and qualitative evidence that such a formulation is an interesting avenue of research.
@article{arxiv.1903.02709,
title = {On Adversarial Mixup Resynthesis},
author = {Christopher Beckham and Sina Honari and Vikas Verma and Alex Lamb and Farnoosh Ghadiri and R Devon Hjelm and Yoshua Bengio and Christopher Pal},
journal= {arXiv preprint arXiv:1903.02709},
year = {2019}
}