Generative Domain Adaptation for Face Anti-Spoofing

被引:19
|
作者
Zhou, Qianyu [1 ]
Zhang, Ke-Yue [2 ]
Yao, Taiping [2 ]
Yi, Ran [1 ]
Sheng, Kekai [2 ]
Ding, Shouhong [2 ]
Ma, Lizhuang [1 ]
机构
[1] Shanghai Jiao Tong Univ, Shanghai, Peoples R China
[2] Tencent, Youtu Lab, Shanghai, Peoples R China
来源
基金
中国国家自然科学基金;
关键词
Face anti-spoofing; Unsupervised domain adaptation; PHASE;
D O I
10.1007/978-3-031-20065-6_20
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 (FAS) approaches based on unsupervised domain adaption (UDA) have drawn growing attention due to promising performances for target scenarios. Most existing UDA FAS methods typically fit the trained models to the target domain via aligning the distribution of semantic high-level features. However, insufficient supervision of unlabeled target domains and neglect of low-level feature alignment degrade the performances of existing methods. To address these issues, we propose a novel perspective of UDA FAS that directly fits the target data to the models, i.e., stylizes the target data to the source-domain style via image translation, and further feeds the stylized data into the well-trained source model for classification. The proposed Generative Domain Adaptation (GDA) framework combines two carefully designed consistency constraints: 1) Inter-domain neural statistic consistency guides the generator in narrowing the inter-domain gap. 2) Dual-level semantic consistency ensures the semantic quality of stylized images. Besides, we propose intra-domain spectrum mixup to further expand target data distributions to ensure generalization and reduce the intra-domain gap. Extensive experiments and visualizations demonstrate the effectiveness of our method against the state-of-the-art methods.
引用
收藏
页码:335 / 356
页数:22
相关论文
共 50 条
  • [1] Unsupervised Domain Adaptation for Face Anti-Spoofing
    Li, Haoliang
    Li, Wen
    Cao, Hong
    Wang, Shiqi
    Huang, Feiyue
    Kot, Alex C.
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2018, 13 (07) : 1794 - 1809
  • [2] Self-Domain Adaptation for Face Anti-Spoofing
    Wang, Jingjing
    Zhang, Jingyi
    Bian, Ying
    Cai, Youyi
    Wang, Chunmao
    Pu, Shiliang
    [J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 2746 - 2754
  • [3] Unsupervised Compound Domain Adaptation for Face Anti-Spoofing
    Panwar, Ankush
    Singh, Pratyush
    Saha, Suman
    Paudel, Danda Pani
    Van Gool, Luc
    [J]. 2021 16TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2021), 2021,
  • [4] FACE ANTI-SPOOFING BASED ON MULTI-LAYER DOMAIN ADAPTATION
    Zhou, Fengshun
    Gao, Chenqiang
    Chen, Fang
    Li, Chaoyu
    Li, Xindou
    Yang, Feng
    Zhao, Yue
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW), 2019, : 192 - 197
  • [5] Source-Free Domain Adaptation With Domain Generalized Pretraining for Face Anti-Spoofing
    Liu, Yuchen
    Chen, Yabo
    Dai, Wenrui
    Gou, Mengran
    Huang, Chun-Ting
    Xiong, Hongkai
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (08) : 5430 - 5448
  • [6] Towards Unsupervised Domain Generalization for Face Anti-Spoofing
    Liu, Yuchen
    Chen, Yabo
    Gou, Mengran
    Huang, Chun-Ting
    Wang, Yaoming
    Dai, Wenrui
    Xiong, Hongkai
    [J]. 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 20597 - 20607
  • [7] Face anti-spoofing methods
    Parveen, Sajida
    Ahmad, Sharifah Mumtazah Syed
    Hanafi, Marsyita
    Adnan, Wan Azizun Wan
    [J]. CURRENT SCIENCE, 2015, 108 (08): : 1491 - 1500
  • [8] Surveillance Face Anti-Spoofing
    Fang, Hao
    Liu, Ajian
    Wan, Jun
    Escalera, Sergio
    Zhao, Chenxu
    Zhang, Xu
    Li, Stan Z.
    Lei, Zhen
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2024, 19 : 1535 - 1546
  • [9] Towards face anti-spoofing
    Syed, Muhammad Ibrahim
    Asif, Amina
    Shahzad, Mohsin
    Khan, Uzair
    Khan, Sumair
    Mahmood, Zahid
    [J]. JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, 2023,
  • [10] A Review on Face Anti-spoofing
    Jiang, Fang-Ling
    Liu, Peng-Cheng
    Zhou, Xiang-Dong
    [J]. Zidonghua Xuebao/Acta Automatica Sinica, 2021, 47 (08): : 1799 - 1821