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
  • [31] Semi-supervised convolutional generative adversarial network for hyperspectral image classification
    Xue, Zhixiang
    [J]. IET IMAGE PROCESSING, 2020, 14 (04) : 709 - 719
  • [32] Semi-supervised feature selection via hierarchical regression for web image classification
    Xiaonan Song
    Jianguang Zhang
    Yahong Han
    Jianmin Jiang
    [J]. Multimedia Systems, 2016, 22 : 41 - 49
  • [33] Semi-Supervised Image Classification Based on Local and Global Regression
    Zhao, Mingbo
    Zhan, Choujun
    Wu, Zhou
    Tang, Peng
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2015, 22 (10) : 1666 - 1670
  • [34] Hybrid Graph Convolutional Network for Semi-Supervised Retinal Image Classification
    Zhang, Guanghua
    Pan, Jing
    Zhang, Zhaoxia
    Zhang, Heng
    Xing, Changyuan
    Sun, Bin
    Li, Ming
    [J]. IEEE ACCESS, 2021, 9 : 35778 - 35789
  • [35] Hyperspectral Image Classification Based on Semi-Supervised Rotation Forest
    Lu, Xiaochen
    Zhang, Junping
    Li, Tong
    Zhang, Ye
    [J]. REMOTE SENSING, 2017, 9 (09)
  • [36] Self-Supervised Assisted Semi-Supervised Residual Network for Hyperspectral Image Classification
    Song, Liangliang
    Feng, Zhixi
    Yang, Shuyuan
    Zhang, Xinyu
    Jiao, Licheng
    [J]. REMOTE SENSING, 2022, 14 (13)
  • [37] Semi-supervised graph-based hyperspectral image classification
    Camps-Valls, Gustavo
    Bandos, Tatyana V.
    Zhou, Dengyong
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2007, 45 (10): : 3044 - 3054
  • [38] Graph-based multimodal semi-supervised image classification
    Xie, Wenxuan
    Lu, Zhiwu
    Peng, Yuxin
    Xiao, Jianguo
    [J]. NEUROCOMPUTING, 2014, 138 : 167 - 179
  • [39] Knowledge-based semi-supervised satellite image classification
    Al Momani, Bilal
    Morrow, Philip
    McClean, Sally
    [J]. 2007 9TH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, VOLS 1-3, 2007, : 264 - 267
  • [40] Adaptive Feature Selection and Feature Fusion for Semi-supervised Classification
    Du, Wei
    Phlypo, Ronald
    Adali, Tulay
    [J]. JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2019, 91 (05): : 521 - 537