The Conditional Boundary Equilibrium Generative Adversarial Network and its Application to Facial Attributes
2019 International Joint Conference on Neural Networks (IJCNN),
doi: 10.1109/IJCNN.2019.8852164
- Jul 2019
Associated documents :
We propose an extension of the Boundary Equilibrium GAN (BEGAN) neural network, named Conditional BEGAN (CBEGAN), as a general generative and transformational
approach for data processing. As a novelty, the system is able
of both data generation and transformation under conditional
input. We evaluate our approach for conditional image generation
and editing using five controllable attributes for images of faces
from the CelebA dataset: age, smiling, cheekbones, eyeglasses and
gender. We perform a set of objective quantitative experiments
to evaluate the models performance and a qualitative user study
to evaluate how humans assess the generated and edited images.
Both evaluations yield coinciding results which show that the
generated facial attributes are recognizable in more than 80%
of all new testing samples.
@InProceedings{MBEW19,
author = {Marzouk, Ahmed and Barros, Pablo and Eppe, Manfred and Wermter, Stefan},
title = {The Conditional Boundary Equilibrium Generative Adversarial Network and its Application to Facial Attributes},
booktitle = {2019 International Joint Conference on Neural Networks (IJCNN)},
editors = {},
number = {},
volume = {},
pages = {},
year = {2019},
month = {Jul},
publisher = {IEEE},
doi = {10.1109/IJCNN.2019.8852164},
}