A semi-supervised network based on feature embeddings for image classification

被引:1
|
作者
Nuhoho, Raphael Elimeli [1 ]
Chen Wenyu [1 ]
Baffour, Adu Asare [2 ]
机构
[1] Univ Elect Sci & Technol China, Computat Intelligence Lab, Sch Comp Sci & Technol, 2006 Xiyuan Ave, Chengdu 611731, Sichuan, Peoples R China
[2] Univ Elect Sci & Technol China, Sch Informat & Software Engn, Chengdu, Peoples R China
关键词
clustering; convolutional neural network; feature embedding; semi-supervised learning;
D O I
10.1111/exsy.12908
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep learning approaches, including convolutional neural networks, are suitable for image classification tasks with well-labelled data. Unfortunately, we do not always have sufficiently labelled data. Recent methods attempt to leverage labelled and unlabelled data using fine-tuning or transfer learning. However, these methods rely on low-level image features. This article departs from recent works and proposes a new semi-supervised learning network that constitutes a convolutional branch and a neighbour cluster branch. Also, we introduce a new loss function that carefully optimizes the network according to the labelled/unlabelled data. In this way, we reduce any tendency to rely on low-level features, which is the case in current methods. We use datasets from three different domains (hand-written digits, natural images, and objects) to analyse the performance of our method. Experimental analysis shows that the network performs better by learning inherent discrimination features when integrating unlabelled data into the model's training process. Our proposed approach also provides strong generalization in the context of transfer learning. Finally, this study shows that the proposed loss function optimizes the network to produce more efficient feature embeddings for domain adaptation.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] Semi-supervised Image Classification Learning Based on Random Feature Subspace
    Liu Li
    Zhang Huaxiang
    Hu Xiaojun
    Sun Feifei
    [J]. PATTERN RECOGNITION (CCPR 2014), PT I, 2014, 483 : 237 - 242
  • [2] A novel feature selection based semi-supervised method for image classification
    Tahir, M. A.
    Smith, J. E.
    Caleb-Solly, P.
    [J]. COMPUTER VISION SYSTEMS, PROCEEDINGS, 2008, 5008 : 484 - 493
  • [3] Semi-supervised feature learning for hyperspectral image classification
    Zhang, Pengfei
    Cao, Liujuan
    Wang, Cheng
    Li, Jonathan
    [J]. 2ND ISPRS INTERNATIONAL CONFERENCE ON COMPUTER VISION IN REMOTE SENSING (CVRS 2015), 2016, 9901
  • [4] Semi-Supervised Feature Transformation for Tissue Image Classification
    Watanabe, Kenji
    Kobayashi, Takumi
    Wada, Toshikazu
    [J]. PLOS ONE, 2016, 11 (12):
  • [5] POLSAR IMAGE CLASSIFICATION BASED-ON SEMI-SUPERVISED POLARIMETRIC FEATURE SELECTION
    Huang, Xiayuan
    [J]. 2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 196 - 200
  • [6] SEMI-SUPERVISED FEATURE LEARNING FOR REMOTE SENSING IMAGE CLASSIFICATION
    Yin, Xiaoshuang
    Yang, Wen
    Xia, Gui-Song
    Dong, Lixia
    [J]. 2014 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2014, : 1261 - 1264
  • [7] A Flexible Semi-supervised Feature Extraction Method for Image Classification
    Dornaika, Fadi
    El Traboulsi, Youssof
    [J]. COMPUTER VISION - ACCV 2014 WORKSHOPS, PT III, 2015, 9010 : 122 - 137
  • [8] Graph convolutional network-based semi-supervised feature classification of volumes
    He, Xiangyang
    Yang, Shuoliu
    Tao, Yubo
    Dai, Haoran
    Lin, Hai
    [J]. JOURNAL OF VISUALIZATION, 2022, 25 (02) : 379 - 393
  • [9] Graph convolutional network-based semi-supervised feature classification of volumes
    Xiangyang He
    Shuoliu Yang
    Yubo Tao
    Haoran Dai
    Hai Lin
    [J]. Journal of Visualization, 2022, 25 : 379 - 393
  • [10] A semi-supervised convolutional neural network based on subspace representation for image classification
    Gatto, Bernardo B.
    Souza, Lincon S.
    dos Santos, Eulanda M.
    Fukui, Kazuhiro
    Junior, Waldir S. S.
    dos Santos, Kenny V.
    [J]. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2020, 2020 (01)