Convolutional Dictionary Pair Learning Network for Image Representation Learning

@article{Zhang2019ConvolutionalDP,
  title={Convolutional Dictionary Pair Learning Network for Image Representation Learning},
  author={Z. Zhang and Yulin Sun and Yang Wang and Z. Zha and S. Yan and Meng Wang},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.12138}
}
  • Z. Zhang, Yulin Sun, +3 authors Meng Wang
  • Published 2019
  • Computer Science, Engineering, Mathematics
  • ArXiv
  • Both the Dictionary Learning (DL) and Convolutional Neural Networks (CNN) are powerful image representation learning systems based on different mechanisms and principles, however whether we can seamlessly integrate them to improve the per-formance is noteworthy exploring. To address this issue, we propose a novel generalized end-to-end representation learning architecture, dubbed Convolutional Dictionary Pair Learning Network (CDPL-Net) in this paper, which integrates the learning schemes of… CONTINUE READING
    A Survey on Concept Factorization: From Shallow to Deep Representation Learning
    • 1
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 46 REFERENCES
    Deep Micro-Dictionary Learning and Coding Network
    • 3
    • Highly Influential
    • PDF
    Dictionary Learning Inspired Deep Network for Scene Recognition
    • 9
    • PDF
    Deep Dictionary Learning
    • 64
    Nonlinear dictionary learning with application to image classification
    • 22
    • PDF
    Majorization Minimization Technique for Optimally Solving Deep Dictionary Learning
    • 9
    • Highly Influential
    • PDF
    Projective dictionary pair learning for pattern classification
    • 211
    • PDF
    Multi-Kernel Low-Rank Dictionary Pair Learning for Multiple Features Based Image Classification
    • 10
    Sparse Representation Based Fisher Discrimination Dictionary Learning for Image Classification
    • 360
    • Highly Influential
    • PDF
    Supervised Deep Sparse Coding Networks
    • 8
    • Highly Influential
    • PDF