Joint Deep Learning of Facial Expression Synthesis and Recognition

被引:25
作者
Yan, Yan [1 ]
Huang, Ying [1 ]
Chen, Si [2 ]
Shen, Chunhua [3 ]
Wang, Hanzi [1 ]
机构
[1] Xiamen Univ, Fujian Key Lab Sensing & Comp Smart City, Sch Informat, Xiamen 361005, Peoples R China
[2] Xiamen Univ Technol, Sch Comp & Informat Engn, Xiamen 361024, Peoples R China
[3] Univ Adelaide, Sch Comp Sci, Adelaide, SA 5005, Australia
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Gallium nitride; Face recognition; Databases; Generative adversarial networks; Deep learning; Training data; Generators; Facial expression recognition; facial expression synthesis; convolutional neural networks (CNNs); generative adversarial net (GAN); NETWORKS; MANIFOLD; IMAGES;
D O I
10.1109/TMM.2019.2962317
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recently, deep learning based facial expression recognition (FER) methods have attracted considerable attention and they usually require large-scale labelled training data. Nonetheless, the publicly available facial expression databases typically contain a small amount of labelled data. In this paper, to overcome the above issue, we propose a novel joint deep learning of facial expression synthesis and recognition method for effective FER. More specifically, the proposed method involves a two-stage learning procedure. Firstly, a facial expression synthesis generative adversarial network (FESGAN) is pre-trained to generate facial images with different facial expressions. To increase the diversity of the training images, FESGAN is elaborately designed to generate images with new identities from a prior distribution. Secondly, an expression recognition network is jointly learned with the pre-trained FESGAN in a unified framework. In particular, the classification loss computed from the recognition network is used to simultaneously optimize the performance of both the recognition network and the generator of FESGAN. Moreover, in order to alleviate the problem of data bias between the real images and the synthetic images, we propose an intra-class loss with a novel real data-guided back-propagation (RDBP) algorithm to reduce the intra-class variations of images from the same class, which can significantly improve the final performance. Extensive experimental results on public facial expression databases demonstrate the superiority of the proposed method compared with several state-of-the-art FER methods.
引用
收藏
页码:2792 / 2807
页数:16
相关论文
共 86 条
  • [1] Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-Related Applications
    Adrian Corneanu, Ciprian
    Oliu Simon, Marc
    Cohn, Jeffrey F.
    Escalera Guerrero, Sergio
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (08) : 1548 - 1568
  • [2] [Anonymous], 2016, ARXIV161005586
  • [3] [Anonymous], 2016, Advances in Face Detection and Facial Image Analysis, DOI 10.1007/978-3-319-25958-1_4
  • [4] [Anonymous], 2018, arXiv:1804.08348
  • [5] [Anonymous], 2018, ABS180201822 CORR
  • [6] [Anonymous], 2017, ARXIV PREPRINT ARXIV
  • [7] [Anonymous], 2014, P 3 INT C LEARN REPR
  • [8] [Anonymous], 2006, Pattern Recognition and Machine Learning
  • [9] [Anonymous], 2016, ARXIV161109961
  • [10] [Anonymous], 2010, TECH REP