Capturing Label Characteristics in VAEs

TL;DR

This paper introduces the CCVAE, a novel VAE model that explicitly captures label characteristics in the latent space, enabling more meaningful and flexible representation learning and data manipulation.

Contribution

The paper proposes CCVAE, a new VAE framework that models label characteristics separately from label values, improving interpretability and manipulation of learned features.

Findings

CCVAE effectively captures meaningful label characteristics.

Enables smooth traversals and diverse conditional generation.

Facilitates transferring characteristics across data points.

Abstract

We present a principled approach to incorporating labels in VAEs that captures the rich characteristic information associated with those labels. While prior work has typically conflated these by learning latent variables that directly correspond to label values, we argue this is contrary to the intended effect of supervision in VAEs-capturing rich label characteristics with the latents. For example, we may want to capture the characteristics of a face that make it look young, rather than just the age of the person. To this end, we develop the CCVAE, a novel VAE model and concomitant variational objective which captures label characteristics explicitly in the latent space, eschewing direct correspondences between label values and latents. Through judicious structuring of mappings between such characteristic latents and labels, we show that the CCVAE can effectively learn meaningful representations of the characteristics of interest across a variety of supervision schemes. In particular, we show that the CCVAE allows for more effective and more general interventions to be performed, such as smooth traversals within the characteristics for a given label, diverse conditional generation, and transferring characteristics across datapoints.