• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Wang, Quanzeng (Wang, Quanzeng.) | Li, Jianqiang (Li, Jianqiang.) | Cheng, Wenxiu (Cheng, Wenxiu.) | Zhao, Linna (Zhao, Linna.)

收录:

EI Scopus

摘要:

Pollen allergy is a common seasonal disease. Current automatic pollen classification methods have high accuracy for high-quality images. However, the imaging process of pollen can produce defocusing blur, and some pollen characteristics have subtle differences, which limits the accuracy of the methods. To address this, we introduce a supervised contrastive learning method to fine-tune the pre-trained classification network and optimize its feature representation ability. We combined multilayer scan images of the same pollen into positive example pairs, and with multilayer scan images of other classes of pollen into negative example pairs. This can learn more similar features of the same class samples and differences of different class samples. We establish a pollen dictionary based on feature representation, compare new test samples with pollen grains in the dictionary, and obtain the final pollen class through weighted voting. Experimental results show that our method is effective for distinguishing easily confused pollen grains. © 2024 ACM.

关键词:

Supervised learning Self-supervised learning Contrastive Learning Federated learning Adversarial machine learning

作者机构:

  • [ 1 ] [Wang, Quanzeng]Beijing University of Technology, Beijing, China
  • [ 2 ] [Li, Jianqiang]Beijing University of Technology, Beijing, China
  • [ 3 ] [Cheng, Wenxiu]Beijing University of Technology, Beijing, China
  • [ 4 ] [Zhao, Linna]Beijing University of Technology, Beijing, China

通讯作者信息:

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

年份: 2024

页码: 7-11

语种: 英文

被引次数:

WoS核心集被引频次:

SCOPUS被引频次:

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:423/4940299
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司