Face-Specific Data Augmentation for Unconstrained Face Recognition
International Journal of Computer Vision, pp. 642-667, 2019.
We identify two issues as key to developing effective face recognition systems: maximizing the appearance variations of training images and minimizing appearance variations in test images. The former is required to train the system for whatever appearance variations it will ultimately encounter and is often addressed by collecting massive...More
Full Text (Upload PDF)
PPT (Upload PPT)