Large-scale Bisample Learning on ID versus Spot Face Recognition

Xiangyu Zhu^1* Hao Liu^1* Zhen Lei¹ Hailin Shi¹ Fan Yang² Dong Yi³ Guojun Qi⁴ Stan Z. Li¹

¹Institute of Automation, Chinese Academy of Sciences

²College of Software, Beihang University

³DAMO Academy, Alibaba Group

⁴HUAWEI Cloud

In real-world face recognition applications, there is a tremendous amount of data with two images for each person. One is an ID photo for face enrollment, and the other is a probe photo captured on spot. Most existing methods are designed for training data with limited breadth (a relatively small number of classes) and sufficient depth (many samples for each class). They would meet great challenges on ID versus Spot (IvS) data, including the under-represented intra-class variations and an excessive demand on computing devices. In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition. To tackle the bisample problem with only two samples for each class, a classification-verification-classification (CVC) training strategy is proposed to progressively enhance the IvS performance. Besides, a dominant prototype softmax (DP-softmax) is incorporated to make the deep learning scalable on large-scale classes. We conduct LBL on a IvS face dataset with more than two million identities. Experimental results show the proposed method achieves superior performance to previous ones, validating the effectiveness of LBL on IvS face recognition.

Updates:

l [new] Public-IvS database released.

Downloads:

[Data]

1. Public-IvS: An IvS test dataset from BaiduBaike and official pages, containing 1,262 identities and 5,503 images. [BaiduYun] [GoogleDrive]