Tri-Branch GAN: A Semi-supervised Method Based on Rebalance

Weiqiang Zhong, Tiankui Zhang, Yapeng Wang, Zeren Chen

研究成果: Conference contribution同行評審

摘要

For deep learning applications in industrial scenarios, few-shot and imbalanced available datasets are very common. Traditional methods usually adopt the idea of hierarchical training, semi-supervised learning and the rebalancing method to train the model respectively, which has certain limitations: Separate trainings does not fully exploit the correlation between the two problems and causes additional computational overhead. Therefore, this paper proposes a semi-supervised learning method based on rebalance, named as Tri-branch GAN (Generative Adversarial Networks). This method makes full use of the correlation between the two problems, avoids the updating coating problem after the model parameter training, and saves the computational cost. Simulation results show that the proposed method can effectively improve the classification accuracy.

原文English
主出版物標題2022 21st International Symposium on Communications and Information Technologies, ISCIT 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面171-176
頁數6
ISBN(電子)9781665498517
DOIs
出版狀態Published - 2022
事件21st International Symposium on Communications and Information Technologies, ISCIT 2022 - Xi'an, China
持續時間: 27 9月 202230 9月 2022

出版系列

名字2022 21st International Symposium on Communications and Information Technologies, ISCIT 2022

Conference

Conference21st International Symposium on Communications and Information Technologies, ISCIT 2022
國家/地區China
城市Xi'an
期間27/09/2230/09/22

指紋

深入研究「Tri-Branch GAN: A Semi-supervised Method Based on Rebalance」主題。共同形成了獨特的指紋。

引用此