Self Residual Attention Network for Deep Face Recognition

• Published in: IEEE access Vol. 7; pp. 55159 - 55168
• Main Authors: Ling, Hefei, Wu, Jiyang, Wu, Lei, Huang, Junrui, Chen, Jiazhong, Li, Ping
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Convolutional neural networks; Discriminative face feature embedding; Embedding; Face; Face recognition; Feature extraction; Feature maps; Feature recognition; Modules; Neural networks; Redundancy; self residual channel attention; self residual spatial attention; Task analysis
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2913205

Discriminative feature embedding is of essential importance in the field of large scale face recognition. In this paper, we propose a self residual attention-based convolutional neural network (SRANet) for discriminative face feature embedding, which aims to learn the long-range dependencies of face images by decreasing the information redundancy among channels and focusing on the most informative components of spatial feature maps. More specifically, the proposed attention module consists of the self channel attention (SCA) block and self spatial attention (SSA) block which adaptively aggregates the feature maps in both channel and spatial domains to learn the inter-channel relationship matrix and the inter-spatial relationship matrix; moreover, matrix multiplications are conducted for a refined and robust face feature. With the attention module we proposed, we can make standard convolutional neural networks (CNNs), such as ResNet-50 and ResNet-101, which have more discriminative power for deep face recognition. The experiments on Labelled Faces in the Wild (LFW), Age Database (AgeDB), Celebrities in Frontal Profile (CFP), and MegaFace Challenge 1 (MF1) show that our proposed SRANet structure consistently outperforms naive CNNs and achieves state-of-the-art performance.