16
views
0
recommends
+1 Recommend
1 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

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

      Read this article at

      ScienceOpenPublisher
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          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.

          Related collections

          Most cited references 9

          • Record: found
          • Abstract: not found
          • Article: not found

          Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Additive Margin Softmax for Face Verification

              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Challenges in representation learning: A report on three machine learning contests

                Bookmark

                Author and article information

                Contributors
                Journal
                CCS
                Cognitive Computation and Systems
                Cogn. Comput. Syst.
                The Institution of Engineering and Technology
                2517-7567
                30 September 2019
                27 November 2019
                December 2019
                : 1
                : 4
                : 97-102
                Affiliations
                Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University , Nanhai Ave 3688, Shenzhen, People's Republic of China
                Article
                CCS.2019.0010 CCS.2019.0010.R1
                10.1049/ccs.2019.0010

                This is an open access article published by the IET in partnership with Shenzhen University under the Creative Commons Attribution License ( http://creativecommons.org/licenses/by/3.0/)

                Page count
                Pages: 0
                Product
                Categories
                Research Article

                Comments

                Comment on this article