ShrinkTeaNet: Million-scale Lightweight Face Recognition via Shrinking Teacher-Student Networks

By Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Ngan T. H. Le. 2019

41 citations recorded by the source corpus.

Large-scale face recognition in-the-wild has been recently achieved matured performance in many real work applications. However, such systems are built on GPU platforms and mostly deploy heavy deep network architectures. Given a high-performance heavy network as a teacher, this work presents a simple and elegant teacher-student learning paradigm, namely ShrinkTeaNet, to train a portable student network that has significantly fewer parameters and competitive accuracy against the teacher network. Far apart from prior teacher-student frameworks mainly focusing on accuracy and compression ratios in closed-set problems, our proposed teacher-student network is proved to be more robust against open-set problem, i.e. large-scale face recognition. In addition, this work introduces a novel Angular Distillation Loss for distilling the feature direction and the sample distributions of the teacher's hypersphere to its student. Then ShrinkTeaNet framework can efficiently guide the student's learning process with the teacher's knowledge presented in both intermediate and last stages of the feature embedding. Evaluations on LFW, CFP-FP, AgeDB, IJB-B and IJB-C Janus, and MegaFace with one million distractors have demonstrated the efficiency of the proposed approach to learn robust student networks which have satisfying accuracy and compact sizes. Our ShrinkTeaNet is able to support the light-weight architecture achieving high performance with 99.77% on LFW and 95.64% on large-scale Megaface protocols.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Xiaogang Wang
3. Luc Van Gool
4. Yi Yang
5. Tao Mei
6. Zhen Lei
7. Trevor Darrell
8. Bernt Schiele

In Signal Processing

1. Zhen Lei
2. Shengcai Liao
3. Dacheng Tao
4. Tao Mei
5. S. Maybank
6. Baosheng Yu
7. Jianping Gou
8. Xiaoming Liu

Citations in the corpus

• Knowledge Distillation: A Survey (2020, background): “…recognition applications, including face recognition (Luo et al. 2016; Kong et al. 2019; Yan et al. 2019; Ge et al. 2018; Wang et al. 2018b, 2019c; Duong et al. 2019; Wu et al. 2020; Wang et al. 2017; Zhang et al. 2020b; Wang et al. 2020b), image/video segmentation (He et al. 2019; Mullapudi et…”
• Exclusivity-Consistency Regularized Knowledge Distillation for Face Recognition (2020, background): “For face recognition model compression, there have been several attempts [16, 40, 51, 26, 19, 52, 18, 35, 9, 10] in literatures to distil large CNNs, so as to make their deployments easier.”