TY - GEN
T1 - Dual Reweighting Domain Generalization for Face Presentation Attack Detection
AU - Liu, Shubao
AU - Zhang, Ke Yue
AU - Yao, Taiping
AU - Sheng, Kekai
AU - Ding, Shouhong
AU - Tai, Ying
AU - Li, Jilin
AU - Xie, Yuan
AU - Ma, Lizhuang
N1 - Publisher Copyright:
© 2021 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85113897657
U2 - 10.24963/ijcai.2021/120
DO - 10.24963/ijcai.2021/120
M3 - 会议稿件
AN - SCOPUS:85113897657
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 867
EP - 873
BT - Proceedings of the 30th International Joint Conference on Artificial Intelligence, IJCAI 2021
A2 - Zhou, Zhi-Hua
PB - International Joint Conferences on Artificial Intelligence
T2 - 30th International Joint Conference on Artificial Intelligence, IJCAI 2021
Y2 - 19 August 2021 through 27 August 2021
ER -