Affiliations: [a] College of Information Science and Engineering, Jiaxing University, Jiaxing, Zhejiang, China | [b] Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, Guangdong, China | [c] College of Computer Science, Sichuan University, Chengdu, Sichuan, China | [d] Chair of Data Management and Biometrics (DMB), Faculty of Electrical Engineering, Computer Science and Mathematics (EEMCS), University of Twente, Enschede, Netherlands | [e] Faculty of Information Technology and Electrical Engineering, Norwegian University of Science and Technology, Gjϕvik, Norway | [f] Artificial Intelligence Laboratory, Sichuan Eface Technology Co., LTD., Chengdu, Sichuan, China
Correspondence:
[*]
Corresponding author: Gaoli Sang, College of Information Science and Engineering, Jiaxing University, Jiaxing, Zhejiang, China. E-mail: glsang@zjxu.edu.cn.
Abstract: Partial face recognition (PFR) is challenging as the appearance of the face changes significantly with occlusion. In particular, these occlusions can be due to any item and may appear in any position that seriously hinders the extraction of discriminative features. Existing methods deal with PFR either by training a deep model with existing face databases containing limited occlusion types or by extracting un-occluded features directly from face regions without occlusions. Limited training data (i.e., occlusion type and diversity) can not cover the real-occlusion situations, and thus training-based methods can not learn occlusion robust discriminative features. The performance of occlusion region-based method is bounded by occlusion detection. Different from limited training data and occlusion region-based methods, we propose to use multi-label attributes for Partial Face Recognition (Attr4PFR). A novel data augmentation is proposed to solve limited training data and generate occlusion attributes. Apart from occlusion attributes, we also include soft biometric attributes and semantic attributes to explore more rich attributes to combat the loss caused by occlusions. To train our Attr4PFR, we propose an implicit attributes loss combined with a softmax loss to enforce Attr4PFR to learn discriminative features. As multi-label attributes are our auxiliary signal in the training phase, we do not need them in the inference. Extensive experiments on public benchmark AR and IJB-C databases show our method is 3% and 2.3% improvement compared to the state-of-the-art.
Keywords: Partial face recognition, multi-label attributes, discriminative feature learning
