Intercategorical Label Interpolation for Emotional Face Generation with Conditional Generative Adversarial Networks
This work addresses a specific challenge in HCI research for generating avatars with continuous emotional expressions, but it is incremental as it builds on existing GAN methods.
The paper tackled the problem of generating emotional face images with continuous features using GANs, despite training data being limited to discrete categorical labels, by exploring label interpolation to enable smooth transitions between affective states.
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.