A Multi-Teacher Assisted Knowledge Distillation Approach for Enhanced Face Image Authentication

Page view(s)
118
Checked on Aug 10, 2025
A Multi-Teacher Assisted Knowledge Distillation Approach for Enhanced Face Image Authentication
Title:
A Multi-Teacher Assisted Knowledge Distillation Approach for Enhanced Face Image Authentication
Journal Title:
Proceedings of the 2023 ACM International Conference on Multimedia Retrieval
Keywords:
Publication Date:
08 June 2023
Citation:
Cheng, T., Zhang, Y., Yin, Y., Zimmermann, R., Yu, Z., & Guo, B. (2023). A Multi-Teacher Assisted Knowledge Distillation Approach for Enhanced Face Image Authentication. Proceedings of the 2023 ACM International Conference on Multimedia Retrieval. https://doi.org/10.1145/3591106.3592280
Abstract:
Recent deep-learning-based face recognition systems have achieved significant success. However, most existing face recognition systems are vulnerable to spoofing attacks where a copy of the face image is used to deceive the authentication. A number of solutions are developed to overcome this problem by building a separate face anti-spoofing model, which however brings in additional storage and computation requirements. Since both recognition and face anti-spoofing tasks stem from the analysis of the same face image, this paper explores a unified approach to reduce the original dualmodel redundancy. To this end, we introduce a compressed multitask model to simultaneously perform both tasks in a lightweight manner, which has the potential to benefit lightweight IoT applications. Concretely, we regard the original two single-task deep models as teacher networks and propose a novel multi-teacher assisted knowledge distillation method to guide our lightweight multi-task model to achieve satisfying performance on both tasks. Additionally, to reduce the large gap between the deep teachers and the light student, a comprehensive feature alignment is further integrated by distilling multi-layer features. Extensive experiments are carried out on two benchmark datasets, where we achieve the task accuracy of 93% meanwhile reducing the model size by 97% and reducing the inference time by 56% compared to the original dual-model.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Ministry of Education (MOE) - Academic Research Fund Tier 2
Grant Reference no. : T2EP20221-0023

This work was supported in part by the National Natural Science Foundation of China (No. 61960206008, 62272390, 62025205, 62072375, 62032020).
Description:
© Author | ACM. 2023. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 2023 ACM International Conference on Multimedia Retrieval. https://doi.org/10.1145/3591106.3592280
ISBN:
979-8-4007-0178-8/23/06
Files uploaded:

File Size Format Action
icmr-main.pdf 1.45 MB PDF Open