EUVIMEDOpdag EUVIMED
Open access · CC BY 3.0

Improved softmax loss for deep learning‐based face and expression recognition

Jiancan Zhou, Xi Jia, Linlin Shen, Zhenkun Wen, Zhong Ming

Cognitive Computation and Systems · 2019

DOI: 10.1049/ccs.2019.0010 ↗

At a glance

Journal article in Cognitive Computation and Systems, 2019. Written by Jiancan Zhou and 4 co-authors. Cited 18 times so far (Crossref); 29 references. The full text is freely available (open access, CC BY 3.0).

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

In recent years, deep convolutional neural networks (CNN) have been widely used in computer vision and significantly improved the performance of image recognition tasks. Most works use softmax loss to supervise the training of CNN and then adopt the output of last layer as features. However, the discriminative capability of the softmax loss is limited. Here, the authors analyse and improve the softmax loss by manipulating the cosine value and input feature length. As the approach does not change the principle of the softmax loss, the network can easily be optimised by typical stochastic gradient descent. The MNIST handwritten digits dataset is employed to visualise the features learned by the improved softmax loss. The CASIA‐WebFace and FER2013 training set are adopted to train deep CNN for face and expression recognition, respectively. Results on both the LFW dataset and FER2013 test set show that the proposed softmax loss can learn more discriminative features and achieve better performance.

Cite

APA

Zhou, J., Jia, X., Shen, L., Wen, Z., & Ming, Z. (2019). Improved softmax loss for deep learning‐based face and expression recognition. Cognitive Computation and Systems. https://doi.org/10.1049/ccs.2019.0010

Vancouver

Zhou J, Jia X, Shen L, Wen Z, Ming Z. Improved softmax loss for deep learning‐based face and expression recognition. Cognitive Computation and Systems. 2019. doi:10.1049/ccs.2019.0010

BibTeX
@article{Zhou2019,
  author = {Zhou, Jiancan and Jia, Xi and Shen, Linlin and Wen, Zhenkun and Ming, Zhong},
  title = {Improved softmax loss for deep learning‐based face and expression recognition},
  journal = {Cognitive Computation and Systems},
  year = {2019},
  doi = {10.1049/ccs.2019.0010}
}
Start for free →