4.7 Article

Salience-Aware Face Presentation Attack Detection via Deep Reinforcement Learning

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIFS.2021.3135748

关键词

Face recognition; Feature extraction; Reinforcement learning; Faces; Videos; Deep learning; Thermal sensors; Face presentation attack detection; deep reinforcement learning; multiscale feature fusion

资金

  1. National Key Research and Development Program of China [2020AAA0108302]
  2. Shenzhen Science and Technology Project [JCYJ20200109143041798]
  3. Beijing Academy of Artificial Intelligence (BAAI)

向作者/读者索取更多资源

The proposed SAFPAD approach utilizes deep reinforcement learning to identify discriminative salient parts in face images, focusing on them to enhance the accuracy and robustness of face presentation attack detection. By jointly training with deep reinforcement learning, the model achieves competitive performance by concentrating on salient local information.
In this paper, we propose a salience-aware face presentation attack detection (SAFPAD) approach, which takes advantage of deep reinforcement learning to exploit the salient local part information in face images. Most existing deep face presentation attack detection approaches extract features from the entire image or several fixed regions. However, the discriminative information beneficial for presentation attack detection is unevenly distributed in the image due to the illumination and presentation attack instrument variation, so treating all regions equally fails to highlight the most discriminative information which is important for more accurate and robust face presentation attack detection. To address this, we propose to identify the discriminative salient parts using deep reinforcement learning and focus on them to alleviate the adverse effects of redundant information in the face images. We fuse the high-level features and the local features which guide the policy network to exploit discriminative patches and assist the classification network to predict more accurate results. We jointly train the SAFPAD model with deep reinforcement learning to generate salient locations. Extensive experiments on five public datasets demonstrate that our approach achieves very competitive performance due to the concentrated employment of salient local information.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据