Multi-layer collaborative optimization fusion for semi-supervised learning

被引:0
|
作者
Ge, Quanbo [1 ]
Liu, Muhua [2 ]
Zhang, Jianchao [3 ]
Song, Jianqiang [2 ]
Zhu, Junlong [2 ]
Zhang, Mingchuan [2 ]
机构
[1] Nanjing Univ Informat Sci & Technol, Sch Automat, Nanjing 210044, Peoples R China
[2] Henan Univ Sci & Technol, Sch Informat Engn, Luoyang 471023, Peoples R China
[3] Qiandao Lake Inst Sci, Hangzhou 311799, Peoples R China
基金
中国国家自然科学基金;
关键词
Collaborative training; Fusion; Image classification; K-means algorithm; Semi-supervised learning;
D O I
10.1016/j.cja.2023.07.032
中图分类号
V [航空、航天];
学科分类号
08 ; 0825 ;
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. (c) 2023 Production and hosting by Elsevier Ltd. on behalf of Chinese Society of Aeronautics and Astronautics. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/).
引用
收藏
页码:342 / 353
页数:12
相关论文
共 50 条
  • [1] Multi-layer collaborative optimization fusion for semi-supervised learning
    Quanbo GE
    Muhua LIU
    Jianchao ZHANG
    Jianqiang SONG
    Junlong ZHU
    Mingchuan ZHANG
    [J]. Chinese Journal of Aeronautics, 2023, (11) : 342 - 353
  • [2] Multi-layer collaborative optimization fusion for semi-supervised learning
    Quanbo GE
    Muhua LIU
    Jianchao ZHANG
    Jianqiang SONG
    Junlong ZHU
    Mingchuan ZHANG
    [J]. Chinese Journal of Aeronautics., 2023, 36 (11) - 353
  • [3] Semi-supervised multi-Layer convolution kernel learning in credit evaluation
    Xu, Lixiang
    Cui, Lixin
    Weise, Thomas
    Li, Xinlu
    Wu, Zhize
    Nie, Feiping
    Chen, Enhong
    Tang, Yuanyan
    [J]. PATTERN RECOGNITION, 2021, 120
  • [4] IML-SSOD: Interconnected and multi-layer threshold learning for semi-supervised detection
    Ge, Bin
    Li, Yuyang
    Liu, Huanhuan
    Xia, Chenxing
    Geng, Shuaishuai
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2024, 103
  • [5] Adaptive collaborative fusion for multi-view semi-supervised classification
    Jiang, Bingbing
    Zhang, Chenglong
    Zhong, Yan
    Liu, Yi
    Zhang, Yingwei
    Wu, Xingyu
    Sheng, Weiguo
    [J]. INFORMATION FUSION, 2023, 96 : 37 - 50
  • [6] Multi-View Collaborative Learning for Semi-Supervised Domain Adaptation
    Ngo, Ba Hung
    Kim, Ju Hyun
    Chae, Yeon Jeong
    Cho, Sung In
    [J]. IEEE ACCESS, 2021, 9 : 166488 - 166501
  • [7] Learning Semi-Supervised Representation Towards a Unified Optimization Framework for Semi-Supervised Learning
    Li, Chun-Guang
    Lin, Zhouchen
    Zhang, Honggang
    Guo, Jun
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 2767 - 2775
  • [8] A federated learning based semi-supervised credit prediction approach enhanced by multi-layer label mean
    Li, Lin
    Long, Sijie
    Bi, Jianxiu
    Wang, Guowei
    Zhang, Jianwei
    Tao, Xiaohui
    [J]. WEB INTELLIGENCE, 2021, 19 (04) : 329 - 342
  • [9] MGCN: Semi-supervised Classification in Multi-layer Graphs with Graph Convolutional Networks
    Ghorbani, Mahsa
    Baghshah, Mahdieh Soleymani
    Rabiee, Hamid R.
    [J]. PROCEEDINGS OF THE 2019 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM 2019), 2019, : 208 - 211
  • [10] Optimization approaches for semi-supervised learning
    Yajima, Y
    Hoshiba, T
    [J]. ICMLA 2005: FOURTH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, PROCEEDINGS, 2005, : 247 - 252