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
  • [41] Unsupervised Domain Adaptation via Risk-Consistent Estimators
    Ding, Feifei
    Li, Jianjun
    Tian, Wanyong
    Zhang, Shanqing
    Yuan, Wenqiang
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 1179 - 1187
  • [42] Unsupervised Domain Adaptation via Class Aggregation for Text Recognition
    Liu, Xiao-Qian
    Ding, Xue-Ying
    Luo, Xin
    Xu, Xin-Shun
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 33 (10) : 5617 - 5630
  • [43] Unsupervised visual domain adaptation via discriminative dictionary evolution
    Songsong Wu
    Guangwei Gao
    Zuoyong Li
    Fei Wu
    Xiao-Yuan Jing
    Pattern Analysis and Applications, 2020, 23 : 1665 - 1675
  • [44] PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training
    Melas-Kyriazi, Luke
    Manrai, Arjun K.
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 12430 - 12440
  • [45] ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation
    Kong, Lingdong
    Quader, Niamul
    Liong, Venice Erin
    2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023), 2023, : 9338 - 9345
  • [46] Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain
    Ren, Chuan-Xian
    Liu, Yong-Hui
    Zhang, Xi-Wen
    Huang, Ke-Kun
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 2122 - 2135
  • [47] Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation
    Park, Sangdon
    Bastani, Osbert
    Weimer, James
    Lee, Insup
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 3219 - 3228
  • [48] Unsupervised Domain Adaptation in the Wild via Disentangling Representation Learning
    Haoliang Li
    Renjie Wan
    Shiqi Wang
    Alex C. Kot
    International Journal of Computer Vision, 2021, 129 : 267 - 283
  • [49] Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
    Mehra, Akshay
    Kailkhura, Bhavya
    Chen, Pin-Yu
    Hamm, Jihun
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021,
  • [50] Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation
    Ni, Jie
    Qiu, Qiang
    Chellappa, Rama
    2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, : 692 - 699