Final published version
Licence: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Real-time facial expression recognition based on iterative transfer learning and efficient attention network
AU - Kong, Y.
AU - Zhang, S.
AU - Zhang, K.
AU - Ni, Q.
AU - Han, J.
PY - 2022/5/31
Y1 - 2022/5/31
N2 - Real-time facial expression recognition is the basis for computers to understand human emotions and detect abnormalities in time. To effectively solve the problems of server overload and privacy information leakage, a real-time facial expression recognition method based on iterative transfer learning and efficient attention network (EAN) for edge resource-constrained scenes is proposed in this paper. Firstly, an EAN is designed with its parameter number and computation amount strictly limited by depth separable convolution and local channel attention mechanism. Then, the soft labels of facial expression data were obtained by EAN based on the idea of knowledge distillation, so as to provide more supervision information for the training process. Finally, an iterative transfer learning method of teacher-student (T-S) network was proposed; it refines the soft labels of the teacher network and further improves the recognition accuracy of the student network. The tests on the public datasets, FER2013 and RAF-DB, show that this method can significantly reduce the model complexity and achieve high recognition accuracy. Compared with other advanced methods, the proposed method strikes a good balance between complexity and accuracy, and well meets the real-time deployment requirements of facial expression recognition technology for edge resource-constrained scenes. © 2022 The Authors. IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.
AB - Real-time facial expression recognition is the basis for computers to understand human emotions and detect abnormalities in time. To effectively solve the problems of server overload and privacy information leakage, a real-time facial expression recognition method based on iterative transfer learning and efficient attention network (EAN) for edge resource-constrained scenes is proposed in this paper. Firstly, an EAN is designed with its parameter number and computation amount strictly limited by depth separable convolution and local channel attention mechanism. Then, the soft labels of facial expression data were obtained by EAN based on the idea of knowledge distillation, so as to provide more supervision information for the training process. Finally, an iterative transfer learning method of teacher-student (T-S) network was proposed; it refines the soft labels of the teacher network and further improves the recognition accuracy of the student network. The tests on the public datasets, FER2013 and RAF-DB, show that this method can significantly reduce the model complexity and achieve high recognition accuracy. Compared with other advanced methods, the proposed method strikes a good balance between complexity and accuracy, and well meets the real-time deployment requirements of facial expression recognition technology for edge resource-constrained scenes. © 2022 The Authors. IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.
KW - Complex networks
KW - Distillation
KW - Face recognition
KW - Learning systems
KW - Edge resources
KW - Facial expression recognition
KW - Human emotion
KW - Real- time
KW - Recognition accuracy
KW - Server overload
KW - Soft labels
KW - Student network
KW - Teachers'
KW - Transfer learning
KW - Iterative methods
U2 - 10.1049/ipr2.12441
DO - 10.1049/ipr2.12441
M3 - Journal article
VL - 16
SP - 1694
EP - 1708
JO - IET Image Processing
JF - IET Image Processing
SN - 1751-9659
IS - 6
ER -