DeepVisage: Making face recognition simple yet with powerful generalization skills
This simplifies face recognition for practitioners by reducing the need for additional tasks like fine-tuning or multi-CNN concatenation, though it is incremental in approach.
The authors tackled the complexity of face recognition methods by proposing a single CNN model trained only with identity labels, achieving state-of-the-art results on datasets like LFW, IJB-A, YouTube Faces, and CACD.
Face recognition (FR) methods report significant performance by adopting the convolutional neural network (CNN) based learning methods. Although CNNs are mostly trained by optimizing the softmax loss, the recent trend shows an improvement of accuracy with different strategies, such as task-specific CNN learning with different loss functions, fine-tuning on target dataset, metric learning and concatenating features from multiple CNNs. Incorporating these tasks obviously requires additional efforts. Moreover, it demotivates the discovery of efficient CNN models for FR which are trained only with identity labels. We focus on this fact and propose an easily trainable and single CNN based FR method. Our CNN model exploits the residual learning framework. Additionally, it uses normalized features to compute the loss. Our extensive experiments show excellent generalization on different datasets. We obtain very competitive and state-of-the-art results on the LFW, IJB-A, YouTube faces and CACD datasets.