Facial Emotion Generation using StarGAN with Differentiable Augmentation

Wava Carissa Putri, Tjan Basaruddin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Emotion generation has remained a challenging task due to the high similarity between each emotion class. In addition, the model had to learn images with various lighting conditions and diverse facial structures. To address this limitation, we propose a modification of StarGAN by applying differentiable augmentation for generating realistic facial emotions. Furthermore, our approach allows both the generator and discriminator to generalize the data better. Finally, we evaluate the performance of the model through an emotion classifier and conduct a quantitative analysis by calculating the accuracy of the generated emotion.

Original languageEnglish
Title of host publicationSPML 2021 - 2021 4th International Conference on Signal Processing and Machine Learning
PublisherAssociation for Computing Machinery
Pages66-71
Number of pages6
ISBN (Electronic)9781450390170
DOIs
Publication statusPublished - 18 Aug 2021
Event4th International Conference on Signal Processing and Machine Learning, SPML 2021 - Virtual, Online, China
Duration: 18 Aug 202120 Aug 2021

Publication series

NameACM International Conference Proceeding Series

Conference

Conference4th International Conference on Signal Processing and Machine Learning, SPML 2021
Country/TerritoryChina
CityVirtual, Online
Period18/08/2120/08/21

Fingerprint

Dive into the research topics of 'Facial Emotion Generation using StarGAN with Differentiable Augmentation'. Together they form a unique fingerprint.

Cite this