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
  • [21] UNSUPERVISED STACKED CAPSULE AUTOENCODER FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Pan, Erting
    Ma, Yong
    Mei, Xiaoguang
    Fan, Fan
    Ma, Jiayi
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 1825 - 1829
  • [22] Representation learning via serial robust autoencoder for domain adaptation
    Yang, Shuai
    Zhang, Yuhong
    Wang, Hao
    Li, Peipei
    Hu, Xuegang
    EXPERT SYSTEMS WITH APPLICATIONS, 2020, 160
  • [23] Dual-aligned unsupervised domain adaptation with graph convolutional networks
    Wu, Fei
    Wei, Pengfei
    Gao, Guangwei
    Hu, Chang-Hui
    Ge, Qi
    Jing, Xiao-Yuan
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (11) : 14979 - 14997
  • [24] Dual-aligned unsupervised domain adaptation with graph convolutional networks
    Fei Wu
    Pengfei Wei
    Guangwei Gao
    Chang-Hui Hu
    Qi Ge
    Xiao-Yuan Jing
    Multimedia Tools and Applications, 2022, 81 : 14979 - 14997
  • [25] COUPLED UNSUPERVISED DEEP CONVOLUTIONAL DOMAIN ADAPTATION FOR SPEECH EMOTION RECOGNITION
    Noi, Ocquaye Elias Nii
    Mao, Qirong
    Xu, Guopeng
    Xue, Yanfei
    2018 IEEE FOURTH INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM), 2018,
  • [26] Convolutional Neural Networks for Road Detection: An Unsupervised Domain Adaptation Approach
    Collegio, Gustavo Rota
    Dal Poz, Aluir Porfirio
    Guimaraes Filho, Antonio Gaudencio
    Habib, Ayman
    MID-TERM SYMPOSIUM THE ROLE OF PHOTOGRAMMETRY FOR A SUSTAINABLE WORLD, VOL. 48-2, 2024, : 65 - 71
  • [27] UNSUPERVISED VISUAL DOMAIN ADAPTATION VIA DICTIONARY EVOLUTION
    Wu, Songsong
    Jing, Xiao-Yuan
    Yue, Dong
    Zhang, Jian
    Yang, Jian
    Yang, Jingyu
    2016 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO (ICME), 2016,
  • [28] Unsupervised domain adaptation via distilled discriminative clustering
    Tang, Hui
    Wang, Yaowei
    Jia, Kui
    PATTERN RECOGNITION, 2022, 127
  • [29] Unsupervised Domain Adaptation via Discriminative Manifold Propagation
    Luo, You-Wei
    Ren, Chuan-Xian
    Dai, Dao-Qing
    Yan, Hong
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (03) : 1653 - 1669
  • [30] Unsupervised Domain Adaptation via Regularized Conditional Alignment
    Cicek, Safa
    Soatto, Stefano
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 1416 - 1425