Applications of cluster-based transfer learning in image and localization tasks

被引:0
|
作者
Yang, Liuyi [1 ]
Finnerty, Patrick [1 ]
Ohta, Chikara [1 ]
机构
[1] Kobe Univ, Grad Sch Syst Informat, Kobe 6578501, Japan
来源
MACHINE LEARNING WITH APPLICATIONS | 2024年 / 18卷
关键词
Semi-supervised transfer learning; Fine-tune; Localization; Image recognition; DOMAIN ADAPTATION;
D O I
10.1016/j.mlwa.2024.100601
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Transfer learning can address the issue of insufficient labels in machine learning. Using knowledge in a labeled domain (source domain) can assist in acquiring and learning knowledge in a domain (target domain) that lacks some or all labels. In this paper, we propose anew cluster-based semi-supervised transfer learning (CBSSTL) under a new assumption that samples in the target domain are unlabeled but contain cluster information. Furthermore, we propose anew transfer learning framework and a method for fine-tuning parameters. We tested and compared the proposed method with other unsupervised and semi-supervised transfer learning methods on well-known image datasets. The experimental results demonstrate the effectiveness of the proposed method. Additionally, we created a localization dataset for transfer learning. Finally, we tested and analyzed the proposed method on this dataset. Its particularly challenging nature makes it difficult for our method to work effectively.
引用
收藏
页数:13
相关论文
共 50 条
  • [41] Image recognition of peanut pod grades based on transfer learning with convolutional neural network
    Zhang R.
    Li Z.
    Hao J.
    Sun L.
    Li H.
    Han P.
    1600, Chinese Society of Agricultural Engineering (36): : 171 - 180
  • [42] Cluster-based Adversarial Decision Boundary for domain-adaptive open set recognition
    Zhong, Jian
    Jiao, Qianfen
    Wu, Si
    Liu, Cheng
    Wong, Hau-San
    KNOWLEDGE-BASED SYSTEMS, 2024, 289
  • [43] Cluster-based adaptive SVM: A latent subdomains discovery method for domain adaptation problems
    Mozafari, Azadeh Sadat
    Jamzad, Mansour
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2017, 162 : 116 - 134
  • [44] Image Based Geo-localization in the Alps
    Saurer, Olivier
    Baatz, Georges
    Koeser, Kevin
    Ladicky, L'ubor
    Pollefeys, Marc
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2016, 116 (03) : 213 - 225
  • [45] Image Based Geo-localization in the Alps
    Olivier Saurer
    Georges Baatz
    Kevin Köser
    L’ubor Ladický
    Marc Pollefeys
    International Journal of Computer Vision, 2016, 116 : 213 - 225
  • [46] Image recognition model of fraudulent websites based on image leader decision and Inception-V3 transfer learning
    Zhou, Shengli
    Xu, Cheng
    Xu, Rui
    Ding, Weijie
    Chen, Chao
    Xu, Xiaoyang
    CHINA COMMUNICATIONS, 2024, 21 (01) : 215 - 227
  • [47] TTL-IQA: Transitive Transfer Learning Based No-Reference Image Quality Assessment
    Yang, Xiaohan
    Li, Fan
    Liu, Hantao
    IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23 : 4326 - 4340
  • [48] Federated deep transfer learning for EEG decoding using multiple BCI tasks
    Wei, Xiaoxi
    Faisal, A. Aldo
    2023 11TH INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING, NER, 2023,
  • [49] Domain- and task-specific transfer learning for medical segmentation tasks
    Zoetmulder, Riaan
    Gavves, Efstratios
    Caan, Matthan
    Marquering, Henk
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2022, 214
  • [50] Image-Based System for Measuring Objects on an Oblique Plane and Its Applications in 2-D Localization
    Lu, Ming-Chih
    Hsu, Chen-Chien
    Lu, Yin-Yu
    IEEE SENSORS JOURNAL, 2012, 12 (06) : 2249 - 2261