SeqFace: Make full use of sequence information for face recognition
This addresses the cost barrier in face recognition research by leveraging video data, though it is incremental as it builds on existing CNN methods.
The authors tackled the problem of expensive high-quality labeled datasets for face recognition by proposing SeqFace, a framework that uses additional unlabeled face sequences from videos to train CNNs, achieving excellent performance on LFW and YTF benchmarks with a single ResNet.
Deep convolutional neural networks (CNNs) have greatly improved the Face Recognition (FR) performance in recent years. Almost all CNNs in FR are trained on the carefully labeled datasets containing plenty of identities. However, such high-quality datasets are very expensive to collect, which restricts many researchers to achieve state-of-the-art performance. In this paper, we propose a framework, called SeqFace, for learning discriminative face features. Besides a traditional identity training dataset, the designed SeqFace can train CNNs by using an additional dataset which includes a large number of face sequences collected from videos. Moreover, the label smoothing regularization (LSR) and a new proposed discriminative sequence agent (DSA) loss are employed to enhance discrimination power of deep face features via making full use of the sequence data. Our method achieves excellent performance on Labeled Faces in the Wild (LFW), YouTube Faces (YTF), only with a single ResNet. The code and models are publicly available on-line (https://github.com/huangyangyu/SeqFace).