• Home
  • Search
  • Improved softmax loss for deep learning‐based face and expression recognition
  • Cite Icon21
  • https://doi.org/10.1049/ccs.2019.0010Copy DOI Icon

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

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

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.

Similar Papers
  • Research Article
  • Citations11

Boosted Additive Angular Margin Loss for breast cancer diagnosis from histopathological images

  • Sep 22, 2023
  • Computers in Biology and Medicine
  • Pendar Alirezazadeh +1
  • Book Chapter
  • Citations127

Soft-Margin Softmax for Deep Classification

  • Jan 01, 2017
  • Xuezhi Liang +4
  • PDF
  • Research Article
  • Citations13

Double Additive Margin Softmax Loss for Face Recognition

  • Dec 19, 2019
  • Applied Sciences
  • Shengwei Zhou +3
  • Conference Article
  • Citations5

A Survey on Loss Functions for Deep Face Recognition Network

  • Sep 08, 2021
  • Aly Khalifa +1
  • Research Article

Facial Emotion Recognition and Synthesis with Convolutional Neural Networks

  • Feb 28, 2026
  • International Journal of Emerging Science and Engineering
  • Karkuzhali S +2
  • Conference Article
  • Citations3134

CosFace: Large Margin Cosine Loss for Deep Face Recognition

  • Jun 01, 2018
  • Hao Wang +7
  • Conference Article
  • Citations20

Face Recognition Based on Densely Connected Convolutional Networks

  • Sep 01, 2018
  • Tong Zhang +4
  • Research Article
  • Citations18

RVFace: Reliable Vector Guided Softmax Loss for Face Recognition.

  • Jan 01, 2022
  • IEEE Transactions on Image Processing
  • Xiaobo Wang +4
  • Book Chapter
  • Citations4544

A Discriminative Feature Learning Approach for Deep Face Recognition

  • Jan 01, 2016
  • Yandong Wen +3
  • Conference Article
  • Citations4

End-to-End Convolutional Neural Network for Speaker Recognition Based on Joint Supervision

  • Jun 01, 2019
  • Wanglei Shi +1
  • Research Article
  • Citations1

Adaptive Hardness Indicator Softmax for Deep Face Recognition

  • Feb 26, 2022
  • International Journal of Pattern Recognition and Artificial Intelligence
  • Mao Cai +4
  • Research Article
  • Citations6

Comparison of Face Recognition and Detection Models: Using Different Convolution Neural Networks

  • Apr 01, 2019
  • Optical Memory and Neural Networks
  • Kai Kang
  • Research Article
  • Citations24

On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Xiangrui Li +3
  • Book Chapter
  • Citations1

Deep Face Recognition Based on Penalty Cosface

  • Jan 01, 2020
  • Shuoyan Lin +3
  • Conference Article
  • Citations3

Contrapositive Margin Softmax Loss for Face Verification

  • Aug 11, 2018
  • Dongxue Xu +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.