Intercategorical Label Interpolation for Emotional Face Generation with Conditional Generative Adversarial Networks

TL;DR

This paper proposes a novel method using label interpolation in conditional GANs to generate emotional face images with smooth transitions between affective states, addressing data limitations in HCI applications.

Contribution

It introduces an intercategorical label interpolation technique to enable continuous emotional feature generation from categorical datasets in GANs.

Findings

Enables generation of faces with continuous emotional features

Improves smoothness of affective state transitions in generated images

Demonstrates effectiveness on emotion-labeled face datasets

Abstract

Generative adversarial networks offer the possibility to generate deceptively real images that are almost indistinguishable from actual photographs. Such systems however rely on the presence of large datasets to realistically replicate the corresponding domain. This is especially a problem if not only random new images are to be generated, but specific (continuous) features are to be co-modeled. A particularly important use case in \emph{Human-Computer Interaction} (HCI) research is the generation of emotional images of human faces, which can be used for various use cases, such as the automatic generation of avatars. The problem hereby lies in the availability of training data. Most suitable datasets for this task rely on categorical emotion models and therefore feature only discrete annotation labels. This greatly hinders the learning and modeling of smooth transitions between displayed affective states. To overcome this challenge, we explore the potential of label interpolation to enhance networks trained on categorical datasets with the ability to generate images conditioned on continuous features.