DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition
arXiv:2002.09859
Abstract
The performance of a convolutional neural network (CNN) based face recognition model largely relies on the richness of labelled training data. Collecting a training set with large variations of a face identity under different poses and illumination changes, however, is very expensive, making the diversity of within-class face images a critical issue in practice. In this paper, we propose a 3D model-assisted domain-transferred face augmentation network (DotFAN) that can generate a series of variants of an input face based on the knowledge distilled from existing rich face datasets collected from other domains. DotFAN is structurally a conditional CycleGAN but has two additional subnetworks, namely face expert network (FEM) and face shape regressor (FSR), for latent code control. While FSR aims to extract face attributes, FEM is designed to capture a face identity. With their aid, DotFAN can learn a disentangled face representation and effectively generate face images of various facial attributes while preserving the identity of augmented faces. Experiments show that DotFAN is beneficial for augmenting small face datasets to improve their within-class diversity so that a better face recognition model can be learned from the augmented dataset.
arXiv comment12 pages, 10 figures
References in corpus (11)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Learning Face Representation from Scratch
- Improved Training of Wasserstein GANs
- CosFace: Large Margin Cosine Loss for Deep Face Recognition
- MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
- Class-Balanced Loss Based on Effective Number of Samples
- Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
- Towards Large-Pose Face Frontalization in the Wild
- Pose-Robust Face Recognition via Deep Residual Equivariant Mapping