Welcome to the InfoSci Platform
Reference Hub1
Rare and Endangered Plant Leaf Identification Method Based on Transfer Learning and Knowledge Distillation

Rare and Endangered Plant Leaf Identification Method Based on Transfer Learning and Knowledge Distillation

Lin Wu, Jingjing Yang, Zhihao Gu, Jiaqian Guo, Xiao Zhang
Copyright: © 2021 |Volume: 12 |Issue: 4 |Pages: 24
ISSN: 1947-3192|EISSN: 1947-3206|EISBN13: 9781799861614|DOI: 10.4018/IJAEIS.288037
Cite Article Cite Article

MLA

Wu, Lin, et al. "Rare and Endangered Plant Leaf Identification Method Based on Transfer Learning and Knowledge Distillation." IJAEIS vol.12, no.4 2021: pp.1-24. http://doi.org/10.4018/IJAEIS.288037

APA

Wu, L., Yang, J., Gu, Z., Guo, J., & Zhang, X. (2021). Rare and Endangered Plant Leaf Identification Method Based on Transfer Learning and Knowledge Distillation. International Journal of Agricultural and Environmental Information Systems (IJAEIS), 12(4), 1-24. http://doi.org/10.4018/IJAEIS.288037

Chicago

Wu, Lin, et al. "Rare and Endangered Plant Leaf Identification Method Based on Transfer Learning and Knowledge Distillation," International Journal of Agricultural and Environmental Information Systems (IJAEIS) 12, no.4: 1-24. http://doi.org/10.4018/IJAEIS.288037

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Considering the limited sample size of rare and endangered plant leaves and the issue that leaf identification is mainly conducted using mobile smart devices and other technology with low computing power, this paper proposes a rare and endangered plant leaf identification method based on transfer learning and knowledge distillation. Following the expansion of data sets containing rare and endangered plant leaves, the last fully connected layer was replaced with trained Alexnet, VGG16, GoogLeNet, and ResNet models to conduct transfer learning, and realized a relatively high success rate in identifying images of these species. Then, knowledge distillation was utilized to transfer Alexnet, VGG16, GoogLeNet, and ResNet models into a lightweight model. The experiment results indicate that, compared with other methods, the lightweight rare and endangered plant identification model trained with the methods described in this paper was not only more accurate but also less complex than its alternatives.