Abstract
Semi-supervised learning is adopted for fine-grained image classification with convolutional networks. Compared with the traditional approach of distillation, we obtain accuracy improvement of ~3 percent points under the upper limit of supervised learning on cassava-disease dataset.
© 2019 The Author(s)
PDF ArticleMore Like This
Yujiao Li and Kuanglu Yu
Th6.63 Optical Fiber Sensors (OFS) 2023
L. Strbkova, P. Vesely, and R. Chmelik
Th3A.39 Digital Holography and Three-Dimensional Imaging (DH) 2019
Aditya Chandra Mandal and Abhijeet Phatak
1263220 European Conference on Biomedical Optics (ECBO) 2023