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 model’s 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}, 
 }