模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2022, Vol. 35 Issue (10): 928-938    DOI: 10.16451/j.cnki.issn1003-6059.202210006
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Contrastive Learning Based on Bilevel Optimization of Pseudo Siamese Networks
CHEN Qingyu1,2,3, JI Fanfan2,3, YUAN Xiaotong2,3,4
1. School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044;
2. Engineering Research Center of Digital Forensics Ministry of Education, Nanjing University of Information Science and Technology, Nanjing 210044;
3. Jiangsu Key Laboratory of Big Data Analysis Technology, Nanjing University of Information Science and Technology, Nanjing 210044;
4. School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044

Download: PDF (2041 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  At present, various designs are applied in contrastive learning algorithms based on pseudo siamese networks to acquire the best student network. However, the performance of teacher network in downstream tasks is ignored. Therefore, an algorithm of contrastive learning based on bilevel optimization of pseudo siamese networks(CLBO)is proposed to acquire the best teacher network by promoting the learning between student and teacher networks. The bilevel optimization strategy includes student network optimization strategy based on nearest neighbor optimization and teacher network optimization strategy based on stochastic gradient descent. The teacher network is regarded as a constraint term through the student network optimization strategy based on nearest neighbor optimization to help the student network learn better from the teacher network. The parameters are calculated by the teacher network optimization strategy based on stochastic gradient descent to update the teacher network. Experiments on 5 datasets show that CLBO performs better than other algorithms in k-NN classification and linear classification tasks. Especially, the advantages of CLBO is obvious when the batch size is smaller.
Key wordsContrastive Learning      Bilevel Optimization      Student Network      Nearest Neighbor Optimization      Teacher Network      Stochastic Gradient Descent     
Received: 29 April 2022     
ZTFLH: TP 391  
Fund:National Key Research and Development Program of China(No.2018AAA0100400), National Natural Science Foun?dation of China(No.U21B2049,61876090,61936005)
Corresponding Authors: YUAN Xiaotong, Ph.D., professor. His research interests include machine learning, image processing and AI+ Meteorology.   
About author:: CHEN Qingyu, master student. His research interests include self-supervised lear-ning.JI Fanfan, Ph.D. candidate. His research interests include deep learning.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
CHEN Qingyu
JI Fanfan
YUAN Xiaotong
Cite this article:   
CHEN Qingyu,JI Fanfan,YUAN Xiaotong. Contrastive Learning Based on Bilevel Optimization of Pseudo Siamese Networks[J]. Pattern Recognition and Artificial Intelligence, 2022, 35(10): 928-938.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202210006      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2022/V35/I10/928
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn