Convolutional Analysis Operator Learning: Acceleration and Convergence

  title={Convolutional Analysis Operator Learning: Acceleration and Convergence},
  author={I. Y. Chun and J. Fessler},
  journal={IEEE Transactions on Image Processing},
  • I. Y. Chun, J. Fessler
  • Published 2020
  • Mathematics, Computer Science, Medicine
  • IEEE Transactions on Image Processing
  • Convolutional operator learning is gaining attention in many signal processing and computer vision applications. Learning kernels has mostly relied on so-called patch-domain approaches that extract and store many overlapping patches across training signals. Due to memory demands, patch-domain methods have limitations when learning kernels from large datasets – particularly with multi-layered structures, e.g., convolutional neural networks – or when applying the learned kernels to high… CONTINUE READING
    Image Reconstruction: From Sparsity to Data-Adaptive Methods and Machine Learning
    • 25
    • PDF
    Convolutional analysis operator learning: Application to sparse-view CT : (Invited Paper)
    • 9
    Convolutional Analysis Operator Learning: Dependence on Training Data
    • 9
    • PDF
    Application of trained Deep BCD-Net to iterative low-count PET image reconstruction
    • 8
    Improved low-count quantitative PET reconstruction with a variational neural network
    • 4
    • PDF
    Image-Domain Material Decomposition Using an Iterative Neural Network for Dual-Energy CT
    • 2
    CAOL from ! { xl } Applying ! to CT MBIR D ⋆ Sinogram ! y Training dataset !


    Publications referenced by this paper.
    ImageNet classification with deep convolutional neural networks
    • 52,445
    • PDF
    Gradient-based learning applied to document recognition
    • 24,402
    • Highly Influential
    • PDF
    $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
    • 6,578
    • Highly Influential
    • PDF
    K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation
    • 5,590
    • Highly Influential
    • PDF
    A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
    • 7,678
    • PDF
    Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
    • 4,473
    • Highly Influential
    • PDF
    Image quality assessment: from error visibility to structural similarity
    • 23,689
    • PDF
    Convex Optimization
    • 34,794
    • Highly Influential
    • PDF
    Online dictionary learning for sparse coding
    • 1,874
    • PDF