Dual Sampling Based Causal Intervention for Face Anti-Spoofing With Identity Debiasing
文献类型：期刊论文
| 作者 | Long, Xingming2,3; Zhang, Jie2,3; Wu, Shuzhe1; Jin, Xin; Shan, Shiguang2,3 |
| 刊名 | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
 |
| 出版日期 | 2024 |
| 卷号 | 19页码:851-862 |
| 关键词 | Causal intervention backdoor adjustment face anti-spoofing out-of-distribution |
| ISSN号 | 1556-6013 |
| DOI | 10.1109/TIFS.2023.3326370 |
| 英文摘要 | Improving generalization to unseen scenarios is one of the greatest challenges in Face Anti-spoofing (FAS). Most previous FAS works focus on domain debiasing to eliminate the distribution discrepancy between training and test data. However, a crucial but usually neglected bias factor is the face identity. Generally, the identity distribution varies across the FAS datasets as the participants in these datasets are from different regions, which will lead to serious identity bias in the cross-dataset FAS tasks. In this work, we resort to causal learning and propose Dual Sampling based Causal Intervention (DSCI) for face anti-spoofing, which improves the generalization of the FAS model by eliminating the identity bias. DSCI treats the bias as a confounder and applies the backdoor adjustment through the proposed dual sampling on the face identity and the FAS feature. Specifically, we first sample the data uniformly on the identity distribution that is obtained by a pretrained face recognition model. By feeding the sampled data into a network, we can get an estimated FAS feature distribution and sample the FAS feature on it. Sampling the FAS feature from a complete estimated distribution can include potential counterfactual features in the training, which effectively expands the training data. The dual sampling process helps the model learn the real causality between the FAS feature and the input liveness, allowing the model to perform more stably across various identity distributions. Extensive experiments demonstrate our proposed method outperforms the state-of-the-art methods on both intra- and cross-dataset evaluations. |
| 资助项目 | National Key Research and Development Program of China |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001119528500017 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/38796]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Shan, Shiguang |
| 作者单位 | 1.Beijing Huawei Cloud Comp Technol Co Ltd, Beijing 100095, Peoples R China 2.Univ Chinese Acad Sci UCAS, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol ICT, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Long, Xingming,Zhang, Jie,Wu, Shuzhe,et al. Dual Sampling Based Causal Intervention for Face Anti-Spoofing With Identity Debiasing[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2024,19:851-862. |
| APA | Long, Xingming,Zhang, Jie,Wu, Shuzhe,Jin, Xin,&Shan, Shiguang.(2024).Dual Sampling Based Causal Intervention for Face Anti-Spoofing With Identity Debiasing.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,19,851-862. |
| MLA | Long, Xingming,et al."Dual Sampling Based Causal Intervention for Face Anti-Spoofing With Identity Debiasing".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 19(2024):851-862. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。