University of Oulu

Z. Yu, J. Wan, Y. Qin, X. Li, S. Z. Li and G. Zhao, "NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 9, pp. 3005-3023, 1 Sept. 2021, doi: 10.1109/TPAMI.2020.3036338

NAS-FAS : static-dynamic central difference network search for face anti-spoofing

Saved in:
Author: Yu, Zitong1; Wan, Jun2; Qin, Yunxiao3;
Organizations: 1Center for Machine Vision and Signal Analysis, University of Oulu, Oulu 90014, Finland
2National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, and University of Chinese Academy of Sciences, Beijing 100190, China
3Northwestern Polytechnical University, Xian 710072, China
4School of Engineering, Westlake University, Hangzhou 310012, China
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 15.8 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2021090645217
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2021-09-06
Description:

Abstract

Face anti-spoofing (FAS) plays a vital role in securing face recognition systems. Existing methods heavily rely on the expert-designed networks, which may lead to a sub-optimal solution for FAS task. Here we propose the first FAS method based on neural architecture search (NAS), called NAS-FAS, to discover the well-suited task-aware networks. Unlike previous NAS works mainly focus on developing efficient search strategies in generic object classification, we pay more attention to study the search spaces for FAS task. The challenges of utilizing NAS for FAS are in two folds: the networks searched on 1) a specific acquisition condition might perform poorly in unseen conditions, and 2) particular spoofing attacks might generalize badly for unseen attacks. To overcome these two issues, we develop a novel search space consisting of central difference convolution and pooling operators. Moreover, an efficient static-dynamic representation is exploited for fully mining the FAS-aware spatio-temporal discrepancy. Besides, we propose Domain/Type-aware Meta-NAS, which leverages cross-domain/type knowledge for robust searching. Finally, in order to evaluate the NAS transferability for cross datasets and unknown attack types, we release a large-scale 3D mask dataset, namely CASIA-SURF 3DMask, for supporting the new ‘cross-dataset cross-type’ testing protocol. Experiments demonstrate that the proposed NAS-FAS achieves state-of-the-art performance on nine FAS benchmark datasets with four testing protocols.

see all

Series: IEEE transactions on pattern analysis and machine intelligence
ISSN: 0162-8828
ISSN-E: 2160-9292
ISSN-L: 0162-8828
Volume: 43
Issue: 9
Pages: 3005 - 3023
DOI: 10.1109/TPAMI.2020.3036338
OADOI: https://oadoi.org/10.1109/TPAMI.2020.3036338
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
Subjects:
Funding: This work was supported by the Academy of Finland for project MiGA (Grant 316765), ICT 2023 project (Grant 328115), Infotech Oulu, and the Chinese National Natural Science Foundation Projects #61961160704, #61876179, Science and Technology Development Fund of Macau No. 0025/2019/A1. The authors also wish to acknowledge CSC-IT Center for Science, Finland.
Academy of Finland Grant Number: 328115
316765
Detailed Information: 328115 (Academy of Finland Funding decision)
316765 (Academy of Finland Funding decision)
Copyright information: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.