TY - GEN
T1 - Facial Emotion Generation using StarGAN with Differentiable Augmentation
AU - Carissa Putri, Wava
AU - Basaruddin, Tjan
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/8/18
Y1 - 2021/8/18
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85119293751&partnerID=8YFLogxK
U2 - 10.1145/3483207.3483218
DO - 10.1145/3483207.3483218
M3 - Conference contribution
AN - SCOPUS:85119293751
T3 - ACM International Conference Proceeding Series
SP - 66
EP - 71
BT - SPML 2021 - 2021 4th International Conference on Signal Processing and Machine Learning
PB - Association for Computing Machinery
T2 - 4th International Conference on Signal Processing and Machine Learning, SPML 2021
Y2 - 18 August 2021 through 20 August 2021
ER -