Multi-layer collaborative optimization fusion for semi-supervised learning  

作　　者：Quanbo GE Muhua LIU Jianchao ZHANG Jianqiang SONG Junlong ZHU Mingchuan ZHANG 

机构地区：[1]School of Automation,Nanjing University of Information Science and Technology,Nanjing 210044,China [2]School of Information Engineering,Henan University of Science and Technology,Luoyang 471023,China [3]Qiandao Lake Institute of Science,Hangzhou 311799,China

出　　处：《Chinese Journal of Aeronautics》2023年第11期342-353,共12页中国航空学报（英文版）

基　　金：supported in part by the National Natural Science Foundation of China(NSFC)(Nos.62033010,62102134);in part by the Leading talents of science and technology in the Central Plain of China(No.224200510004);in part by the Key R&D projects in Henan Province,China(No.231111222600);in part by the Aeronautical Science Foundation of China(No.2019460T5001);in part by the Scientific and Technological Innovation Talents of Colleges and Universities in Henan Province,China(No.22HASTIT014).

摘　　要：Recently,the Cooperative Training Algorithm(CTA),a well-known Semi-Supervised Learning(SSL)technique,has garnered significant attention in the field of image classification.However,traditional CTA approaches face challenges such as high computational complexity and low classification accuracy.To overcome these limitations,we present a novel approach called Weighted fusion based Cooperative Training Algorithm(W-CTA),which leverages the cooperative training technique and unlabeled data to enhance classification performance.Moreover,we introduce the K-means Cooperative Training Algorithm(km-CTA)to prevent the occurrence of local optima during the training phase.Finally,we conduct various experiments to verify the performance of the proposed methods.Experimental results show that W-CTA and km-CTA are effective and efficient on CIFAR-10 dataset.

关 键 词：Collaborative training FUSION Image classification K-means algorithm Semi-supervised learning 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]