Improved cross entropy loss for noisy labels in vision leaf disease classification

Author:

Chen Yipeng12,Xu Ke2ORCID,Zhou Peng3,Ban Xiaojuan1,He Di1

Affiliation:

1. School of Computer & Communication Engineering University of Science and Technology Beijing Beijing China

2. Collaborative Innovation Center of Steel Technology University of Science and Technology Beijing Beijing China

3. Institute of Artificial Intelligence University of Science and Technology Beijing Beijing China

Funder

National Natural Science Foundation of China

Publisher

Institution of Engineering and Technology (IET)

Subject

Electrical and Electronic Engineering,Computer Vision and Pattern Recognition,Signal Processing,Software

Reference33 articles.

1. Deep learning in agriculture: A survey

2. Jacob G. Ehud B.:Training deep neural‐networks using a noise adaptation layer. Paper presented at5th international conference on learning representations Toulon France 24–26 April 2017

3. Filipe R.C. Gustavo C.:A Survey on Deep Learning with Noisy Labels: How to train your model when you cannot trust on the annotations?In:33rd SIBGRAPI Conference on Graphics Patterns and Images pp.9–16.IEEE Piscataway(2020)

4. Sunil T. et al.:Combating label noise in deep learning using abstention. In:Proceedings of the 36th International Conference on Machine Learning pp.6234–6243.ACM New York(2019)

5. Lei F. et al.:Can cross entropy loss be robust to label noise?In:Proceedings of the Twenty‐Ninth International Joint Conference on Artificial Intelligence pp.2206–2212.AAAI Press Palo Alto(2020)

Cited by 8 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3