CoupleFace: Relation Matters for Face Recognition Distillation
Jiaheng Liu, Haoyu Qin, Yichao Wu, Jinyang Guo, Ding Liang, Ke Xu

TL;DR
This paper introduces CoupleFace, a face recognition distillation method that incorporates mutual relation knowledge transfer to enhance student model performance, outperforming existing methods and winning a challenge.
Contribution
It proposes Mutual Relation Distillation (MRD) and Relation-Aware Distillation (RAD) to transfer relation knowledge, improving face recognition distillation beyond feature consistency methods.
Findings
Outperforms existing face recognition distillation methods.
Achieved first place in ICCV21 Masked Face Recognition Challenge.
Demonstrates significant improvements on multiple benchmark datasets.
Abstract
Knowledge distillation is an effective method to improve the performance of a lightweight neural network (i.e., student model) by transferring the knowledge of a well-performed neural network (i.e., teacher model), which has been widely applied in many computer vision tasks, including face recognition. Nevertheless, the current face recognition distillation methods usually utilize the Feature Consistency Distillation (FCD) (e.g., L2 distance) on the learned embeddings extracted by the teacher and student models for each sample, which is not able to fully transfer the knowledge from the teacher to the student for face recognition. In this work, we observe that mutual relation knowledge between samples is also important to improve the discriminative ability of the learned representation of the student model, and propose an effective face recognition distillation method called CoupleFace…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsFace recognition and analysis · Face and Expression Recognition · Domain Adaptation and Few-Shot Learning
Methods1-Dimensional Convolutional Neural Networks
