Poster
On Adversarial Mixup Resynthesis
Christopher Beckham · Sina Honari · Alex Lamb · Vikas Verma · Farnoosh Ghadiri · R Devon Hjelm · Yoshua Bengio · Chris Pal
East Exhibition Hall B + C #61
Keywords: [ Algorithms -> Adversarial Learning; Deep Learning -> Deep Autoencoders; Deep Learning ] [ Generative Models ] [ Unsupervised Learning ] [ Algorithms ]
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.
Live content is unavailable. Log in and register to view live content