TY - JOUR
T1 - Learning Inter and Intra Class Variation with Deep Frequency Factorization Network for Face Anti-Spoofing
AU - Liu, Weihua
AU - Li, Qiuyu
AU - Luo, Yiming
AU - Pan, Yushan
AU - Ding, Weiping
AU - Wang, Hao
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2024
Y1 - 2024
N2 - In this paper, we aim to enhance the generalization ability of single-shot face anti-spoofing tasks in two aspects: 1) we establish a deep frequency factorization network (DFF-Net) to capture deep frequency information, enabling better discrimination of multiple styles of face spoofing, including both 2D and 3D methods; 2) aided by a sample redistribution strategy, we construct a unified anomaly metric-based supervision system to address unknown face attacks. Specifically, the proposed DFF-Net explicitly extracts spoofing cues from the high, low, and fusion frequency domains by embedding a deep frequency filter module into each frequency branch. Furthermore, the devised sample redistribution strategy enables the reorganization of learned features, making them more suitable for the three types of anomaly metric-based supervisions that correspond to the three frequency branches. This approach facilitates iterative learning of the importance of spoofing cues. Experimental results demonstrate that our proposed framework achieves state-of-the-art performance on both monocular and multi-spectral benchmark datasets.
AB - In this paper, we aim to enhance the generalization ability of single-shot face anti-spoofing tasks in two aspects: 1) we establish a deep frequency factorization network (DFF-Net) to capture deep frequency information, enabling better discrimination of multiple styles of face spoofing, including both 2D and 3D methods; 2) aided by a sample redistribution strategy, we construct a unified anomaly metric-based supervision system to address unknown face attacks. Specifically, the proposed DFF-Net explicitly extracts spoofing cues from the high, low, and fusion frequency domains by embedding a deep frequency filter module into each frequency branch. Furthermore, the devised sample redistribution strategy enables the reorganization of learned features, making them more suitable for the three types of anomaly metric-based supervisions that correspond to the three frequency branches. This approach facilitates iterative learning of the importance of spoofing cues. Experimental results demonstrate that our proposed framework achieves state-of-the-art performance on both monocular and multi-spectral benchmark datasets.
KW - convolutional neural network (CNN)
KW - deep learning
KW - Face anti-spoofing
KW - multi-modality fusion
UR - http://www.scopus.com/inward/record.url?scp=85205317548&partnerID=8YFLogxK
U2 - 10.1109/TETCI.2024.3462172
DO - 10.1109/TETCI.2024.3462172
M3 - Article
AN - SCOPUS:85205317548
SN - 2471-285X
JO - IEEE Transactions on Emerging Topics in Computational Intelligence
JF - IEEE Transactions on Emerging Topics in Computational Intelligence
ER -