University of Oulu

Liu, M., Mu, J., Yu, Z., Ruan, K., Shu, B., & Yang, J. (2021). Adversarial learning and decomposition-based domain generalization for face anti-spoofing. Pattern Recognition Letters. https://doi.org/10.1016/j.patrec.2021.10.014

Adversarial learning and decomposition-based domain generalization for face anti-spoofing

Saved in:
Author: Liu, Mingxin1; Mu, Jiong1; Yu, Zitong2;
Organizations: 1Sichuan Agricultural University, Ya’an, Sichuan Province 625000, China
2Center for Machine Vision and Signal Analysis, University of Oulu, Oulu 90014, Finland
Format: article
Version: accepted version
Access: embargoed
Persistent link: http://urn.fi/urn:nbn:fi-fe202201101661
Language: English
Published: Elsevier, 2021
Publish Date: 2023-10-14
Description:

Abstract

Face anti-spoofing (FAS) plays a critical role in the face recognition community for securing the face presentation attacks. Many works have been proposed to regard FAS as a domain generalization problem for robust deployment in real-world scenarios. However, existing methods focus on extracting intrinsic spoofing cues to improve the generalization ability, yet neglect to train a robust classifier. In this paper, we propose a framework to improve the generalization ability of face anti-spoofing in two folds:) a generalized feature space is obtained via aggregation of all live faces while dispersing each domain’s spoof faces; and) a domain agnostic classifier is trained through low-rank decomposition. Specifically, a Common Specific Decomposition for Specific (CSD-S) layer is deployed in the last layer of the network to select common features while discarding domain-specific ones among multiple source domains. The above-mentioned two components are integrated into an end-to-end framework, ensuring the generalization ability to unseen scenarios. The extensive experiments demonstrate that the proposed method achieves state-of-the-art results on four public datasets, including CASIA-MFSD, MSU-MFSD, Replay-Attack, and OULU-NPU.

see all

Series: Pattern recognition letters
ISSN: 0167-8655
ISSN-E: 1872-7344
ISSN-L: 0167-8655
Volume: In press
DOI: 10.1016/j.patrec.2021.10.014
OADOI: https://oadoi.org/10.1016/j.patrec.2021.10.014
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
Subjects:
Funding: This study was financially supported by Sichuan Science and Technology Innovation Seedling Project Funding Project under Grant no. 2019025, Sichuan Agricultural University Innovation and Entrepreneurship Training Program (Grant no. 201910626026).
Copyright information: © 2021. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/.
  https://creativecommons.org/licenses/by-nc-nd/4.0/