Dual Reweighting Domain Generalization for Face Presentation Attack Detection

被引:0
|
作者
Liu, Shubao [1 ,2 ]
Zhang, Ke-Yue [2 ]
Yao, Taiping [2 ]
Sheng, Kekai [2 ]
Ding, Shouhong [2 ]
Tai, Ying [2 ]
Li, Jilin [2 ]
Xie, Yuan [1 ]
Ma, Lizhuang [1 ]
机构
[1] East China Normal Univ, Shanghai, Peoples R China
[2] Tencent, Youtu Lab, Shanghai, Peoples R China
来源
PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021 | 2021年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Face anti-spoofing approaches based on domain generalization (DG) have drawn growing attention due to their robustness for unseen scenarios. Previous methods treat each sample from multiple domains indiscriminately during the training process, and endeavor to extract a common feature space to improve the generalization. However, due to complex and biased data distribution, directly treating them equally will corrupt the generalization ability. To settle the issue, we propose a novel Dual Reweighting Domain Generalization (DRDG) framework which iteratively reweights the relative importance between samples to further improve the generalization. Concretely, Sample Reweighting Module is first proposed to identify samples with relatively large domain bias, and reduce their impact on the overall optimization. Afterwards, Feature Reweighting Module is introduced to focus on these samples and extract more domain-irrelevant features via a self-distilling mechanism. Combined with the domain discriminator, the iteration of the two modules promotes the extraction of generalized features. Extensive experiments and visualizations are presented to demonstrate the effectiveness and interpretability of our method against the state-of-the-art competitors.
引用
收藏
页码:867 / 873
页数:7
相关论文
共 50 条
  • [21] Face presentation attack detection: Research opportunities and perspectives
    Favorskaya, Margarita N.
    INTELLIGENT DECISION TECHNOLOGIES-NETHERLANDS, 2023, 17 (01): : 159 - 193
  • [22] Asymmetric Modality Translation for Face Presentation Attack Detection
    Li, Zhi
    Li, Haoliang
    Luo, Xin
    Hu, Yongjian
    Lam, Kwok-Yan
    Kot, Alex C.
    IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 62 - 76
  • [23] Unknown Presentation Attack Detection with Face RGB Images
    Xiong, Fei
    AbdAlmageed, Wael
    2018 IEEE 9TH INTERNATIONAL CONFERENCE ON BIOMETRICS THEORY, APPLICATIONS AND SYSTEMS (BTAS), 2018,
  • [24] Learning by Environment Clusters for Face Presentation Attack Detection
    Matsunami, Tomoaki
    Uchida, Hidetsugu
    Abe, Narishige
    Yamada, Shigefumi
    PROCEEDINGS OF THE 20TH INTERNATIONAL CONFERENCE OF THE BIOMETRICS SPECIAL INTEREST GROUP (BIOSIG 2021), 2021, 315
  • [25] Face Presentation Attack Detection via Spatiotemporal Autoencoder
    Yilmaz, Selim F.
    Kozat, Suleyman S.
    2020 28TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2020,
  • [26] An exploratory study of interpretability for face presentation attack detection
    Sequeira, Ana F.
    Goncalves, Tiago
    Silva, Wilson
    Pinto, Joao Ribeiro
    Cardoso, Jaime S.
    IET BIOMETRICS, 2021, 10 (04) : 441 - 455
  • [27] Face Presentation Attack Detection by Exploring Spectral Signatures
    Raghavendra, R.
    Raja, Kiran B.
    Venkatesh, Sushma
    Busch, Christoph
    2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, : 672 - 679
  • [28] PRESENTATION ATTACK DETECTION ALGORITHM FOR FACE AND IRIS BIOMETRICS
    Raghavendra, R.
    Busch, Christoph
    2014 PROCEEDINGS OF THE 22ND EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2014, : 1387 - 1391
  • [29] UNSEEN FACE PRESENTATION ATTACK DETECTION WITH HYPERSPHERE LOSS
    Li, Zhi
    Li, Haoliang
    Lam, Kwok-Yan
    Kot, Alex Chichung
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 2852 - 2856
  • [30] Face Image Quality Estimation on Presentation Attack Detection
    Aravena, Carlos
    Pasmino, Diego
    Tapia, Juan
    Busch, Christoph
    PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, CIARP 2023, PT I, 2024, 14469 : 358 - 373