Unsupervised Domain Adaptation via Stacked Convolutional Autoencoder

被引:0
|
作者
Zhu, Yi [1 ,2 ]
Zhou, Xinke [2 ]
Wu, Xindong [1 ,3 ]
机构
[1] Hefei Univ Technol, Hefei 230009, Peoples R China
[2] Yangzhou Univ, Yangzhou 225012, Peoples R China
[3] Hefei Univ Technol, Key Lab Knowledge Engn Big Data, Minist Educ China, Hefei 230009, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 01期
基金
中国国家自然科学基金;
关键词
domain adaptation; convolutional autoencoder; sparse autoencoder;
D O I
10.3390/app13010481
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Unsupervised domain adaptation involves knowledge transfer from a labeled source to unlabeled target domains to assist target learning tasks. A critical aspect of unsupervised domain adaptation is the learning of more transferable and distinct feature representations from different domains. Although previous investigations, using, for example, CNN-based and auto-encoder-based methods, have produced remarkable results in domain adaptation, there are still two main problems that occur with these methods. The first is a training problem for deep neural networks; some optimization methods are ineffective when applied to unsupervised deep networks for domain adaptation tasks. The second problem that arises is that redundancy of image data results in performance degradation in feature learning for domain adaptation. To address these problems, in this paper, we propose an unsupervised domain adaptation method with a stacked convolutional sparse autoencoder, which is based on performing layer projection from the original data to obtain higher-level representations for unsupervised domain adaptation. More specifically, in a convolutional neural network, lower layers generate more discriminative features whose kernels are learned via a sparse autoencoder. A reconstruction independent component analysis optimization algorithm was introduced to perform individual component analysis on the input data. Experiments undertaken demonstrated superior classification performance of up to 89.3% in terms of accuracy compared to several state-of-the-art domain adaptation methods, such as SSRLDA and TLMRA.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] Unsupervised urban scene segmentation via domain adaptation
    Gao, Lianli
    Zhang, Yiyue
    Zou, Fuhao
    Shao, Jie
    Lai, Junyu
    NEUROCOMPUTING, 2020, 406 : 295 - 301
  • [32] Video surveillance image enhancement via a convolutional neural network and stacked denoising autoencoder
    Che Aminudin, Muhamad Faris
    Suandi, Shahrel Azmin
    NEURAL COMPUTING & APPLICATIONS, 2022, 34 (04): : 3079 - 3095
  • [33] Video surveillance image enhancement via a convolutional neural network and stacked denoising autoencoder
    Muhamad Faris Che Aminudin
    Shahrel Azmin Suandi
    Neural Computing and Applications, 2022, 34 : 3079 - 3095
  • [34] UNSUPERVISED DOMAIN ADAPTATION VIA DOMAIN ADVERSARIAL TRAINING FOR SPEAKER RECOGNITION
    Wang, Qing
    Rao, Wei
    Sun, Sining
    Xie, Lei
    Chng, Eng Siong
    Li, Haizhou
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 4889 - 4893
  • [35] Spectral Bisection Tree Guided Deep Adaptive Exemplar Autoencoder for Unsupervised Domain Adaptation
    Shao, Ming
    Ding, Zhengming
    Zhao, Handong
    Fu, Yun
    THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 2023 - 2029
  • [36] Invertible Autoencoder for Domain Adaptation
    Teng, Yunfei
    Choromanska, Anna
    COMPUTATION, 2019, 7 (02)
  • [37] UNSUPERVISED DEEP HASHING WITH STACKED CONVOLUTIONAL AUTOENCODERS
    En, Sovann
    Cremilleux, Bruno
    Jurie, Frederic
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 3420 - 3424
  • [38] Unsupervised domain adaptation via softmax-based prototype construction and adaptation
    Li, Jingyao
    Lu, Shuai
    Li, Zhanshan
    INFORMATION SCIENCES, 2022, 609 : 257 - 275
  • [39] Subdomain adaptation via correlation alignment with entropy minimization for unsupervised domain adaptation
    Gilo, Obsa
    Mathew, Jimson
    Mondal, Samrat
    Sandoniya, Rakesh Kumar
    PATTERN ANALYSIS AND APPLICATIONS, 2024, 27 (01)
  • [40] Unsupervised change detection using hierarchical convolutional autoencoder
    Bergamasco, Luca
    Bovolo, Francesca
    Bruzzone, Lorenzo
    IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXVI, 2020, 11533