On Adversarial Mixup Resynthesis

TL;DR

This paper introduces a novel auto-encoder based approach that combines multiple inputs through adversarial training and interpolation in latent space, enhancing semi-supervised learning and data synthesis.

Contribution

It proposes a new method for combining learned representations using adversarial mixup resynthesis, with applications in semi-supervised learning and data generation.

Findings

Effective interpolation of latent representations

Improved semi-supervised learning performance

Qualitative and quantitative validation of the approach

Abstract

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.