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
  • [1] Unsupervised domain adaptation forword sense disambiguation using stacked denoising autoencoder
    Ibaraki University, Department of Computer and Information Sciences, 4-12-1 Nakanarusawa, Hitachi, Ibaraki
    316-8511, Japan
    Pac. Asia Conf. Lang., Inf. Comput., PACLIC, (224-231):
  • [2] Representation learning via an integrated autoencoder for unsupervised domain adaptation
    Zhu, Yi
    Wu, Xindong
    Qiang, Jipeng
    Yuan, Yunhao
    Li, Yun
    FRONTIERS OF COMPUTER SCIENCE, 2023, 17 (05)
  • [3] Deep Unsupervised Convolutional Domain Adaptation
    Zhuo, Junbao
    Wang, Shuhui
    Zhang, Weigang
    Huang, Qingming
    PROCEEDINGS OF THE 2017 ACM MULTIMEDIA CONFERENCE (MM'17), 2017, : 261 - 269
  • [4] Unsupervised domain adaptation with Joint Adversarial Variational AutoEncoder
    Li, Yuze
    Zhang, Yan
    Yang, Chunling
    KNOWLEDGE-BASED SYSTEMS, 2022, 250
  • [5] VARIATIONAL AUTOENCODER BASED UNSUPERVISED DOMAIN ADAPTATION FOR SEMANTIC SEGMENTATION
    Li, Zongyao
    Togo, Ren
    Ogawa, Takahiro
    Haseyama, Miki
    2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 2426 - 2430
  • [6] Unsupervised Domain Adaptation via Variational Autoencoder with Explicit and Implicit Feature Alignment for Cardiac Segmentation
    Li, Yan
    Wang, Yifan
    Zheng, Fan
    Cheng, Linkai
    Xu, Di
    Cui, Hengfei
    2023 8TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND BIG DATA ANALYTICS, ICCCBDA, 2023, : 532 - 537
  • [7] Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
    Aljundi, Rahaf
    Tuytelaars, Tinne
    COMPUTER VISION - ECCV 2016 WORKSHOPS, PT III, 2016, 9915 : 508 - 515
  • [8] UNSUPERVISED DOMAIN ADAPTATION FOR ROBUST SPEECH RECOGNITION VIA VARIATIONAL AUTOENCODER-BASED DATA AUGMENTATION
    Hsu, Wei-Ning
    Zhang, Yu
    Glass, James
    2017 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2017, : 16 - 23
  • [9] Autoencoder-based Unsupervised Domain Adaptation for Speech Emotion Recognition
    Deng, Jun
    Zhang, Zixing
    Eyben, Florian
    Schuller, Bjoern
    IEEE SIGNAL PROCESSING LETTERS, 2014, 21 (09) : 1068 - 1072
  • [10] Deep cycle autoencoder for unsupervised domain adaptation with generative adversarial networks
    Zhou, Qiang
    Zhou, Wen'an
    Yang, Bin
    Huan, Jun
    IET COMPUTER VISION, 2019, 13 (07) : 659 - 665