A Two-Stage Active Learning Method for Image Classification

Feiyue Wang, Xu Li, Yifan Zhang, Baoguo Wei, Lixin Li

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Recent successes in learning-based image classification rely heavily on a large number of annotated training samples, which often require considerable human effort. In this paper, we propose a new two-stage active learning (AL) method for image classification with a query strategy considering both uncertainty and diversity. In the first stage, the uncertainty is used to determine the candidate set. In the second stage, the candidate set is clustered, and the nearest sample from the cluster center is selected to increase the diversity of samples. Our method uses Poly-1 loss as the classification loss and Binary Cross Entropy (BCE) as the binary loss to distinguish between the labeled samples and the unlabeled samples. We train the two classifiers in a joint way and evaluate our method on the CIFAR10 and CIFAR100 datasets. The rich experimental results show that the proposed method outperforms the state-of-the-art AL methods in image classification tasks.

源语言英语
主期刊名ICIEA 2022 - Proceedings of the 17th IEEE Conference on Industrial Electronics and Applications
编辑Wenxiang Xie, Shibin Gao, Xiaoqiong He, Xing Zhu, Jingjing Huang, Weirong Chen, Lei Ma, Haiyan Shu, Wenping Cao, Lijun Jiang, Zeliang Shu
出版商Institute of Electrical and Electronics Engineers Inc.
1134-1139
页数6
ISBN(电子版)9781665409841
DOI
出版状态已出版 - 2022
活动17th IEEE Conference on Industrial Electronics and Applications, ICIEA 2022 - Chengdu, 中国
期限: 16 12月 202219 12月 2022

出版系列

姓名ICIEA 2022 - Proceedings of the 17th IEEE Conference on Industrial Electronics and Applications

会议

会议17th IEEE Conference on Industrial Electronics and Applications, ICIEA 2022
国家/地区中国
Chengdu
时期16/12/2219/12/22

指纹

探究 'A Two-Stage Active Learning Method for Image Classification' 的科研主题。它们共同构成独一无二的指纹。

引用此