Live briefing
Everything about Convolutional sparse coding
Neural network coding model
The convolutional sparse coding paradigm is an extension of the global sparse coding model, in which a redundant dictionary is modeled as a concatenation of circulant matrices. While the global sparsity constraint describes signal as a linear combination of a few atoms in the redundant dictionary, usually expressed as for a sparse vector, the alternative dictionary structure adopted by the convolutional sparse coding model allows the sparsity prior to be applied locally instead of globally: independent patches of are generated by "local" dictionaries operating over stripes of. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Convolutional sparse codingA 5-minute orientation
- Skim a recent paper: Interpretable Multi-Modal Image Registration Network Based on Disentangled Convolutional Sparse CodingInfluential work since 2022
- Pick up a classic book: Programming Massively Parallel ProcessorsThe most-reprinted book on the subject
- Read the landmark paper: Convolutional Sparse Coding for Compressed Sensing CT ReconstructionCited 137 times
- Go sideways: Sparse dictionary learningA closely related topic
- Go sideways: Sparse approximationA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
Convolutional Sparse Coding for Compressed Sensing CT Reconstruction
Working Locally Thinking Globally: Theoretical Guarantees for Convolutional Sparse Coding
Convolutional Sparse Coding for High Dynamic Range Imaging
Convolutional Sparse Coding for Trajectory Reconstruction
Fast convolutional sparse coding using matrix inversion lemma
Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restoration
Convolutional Sparse and Low-Rank Coding-Based Image Decomposition
Scalable Online Convolutional Sparse Coding
🆕 Influential since 2022
Interpretable Multi-Modal Image Registration Network Based on Disentangled Convolutional Sparse Coding
Revisiting Convolutional Sparse Coding for Image Denoising: From a Multi-Scale Perspective
Convolutional Sparse Coding Based Channel Estimation for OTFS-SCMA in Uplink
Deep High-Order Tensor Convolutional Sparse Coding for Hyperspectral Image Classification
Damage localization with Lamb waves using dense convolutional sparse coding network
📚 Books worth reading
Programming Massively Parallel ProcessorsDavid Kirk, Wen-Mei W. Hwu · 2010
Information Theory, Inference & Learning AlgorithmsDavid J.C. MacKay · 2003
Linear Algebra and Learning from DataGilbert Strang · 2019
Advances in Neural Networks – ISNN 2013Chengan Guo · 2013
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Sparse dictionary learning Sparse dictionary learning (also known as sparse coding or SDL) is a representation learning method which aims to find a sparse representation of the input…
- Sparse approximation Sparse approximation (also known as sparse representation) theory deals with sparse solutions for systems of linear equations. Techniques for finding these…
- K q-flats In data mining and machine learning, k q-flats algorithm is an iterative method which aims to partition m observations into k clusters where each cluster…
- Matching pursuit Matching pursuit (MP) is a sparse approximation algorithm which finds the "best matching" projections of multidimensional data onto the span of an over-complete…
- K-SVD In applied mathematics, k-SVD is a dictionary learning algorithm for creating a dictionary for sparse representations, via a singular value decomposition…
- Spark (mathematics) In mathematics, more specifically in linear algebra, the spark of a m×n matrix A is the smallest integer k such that there exists a set of k columns in…
- Green's theorem In vector calculus, Green's theorem relates a line integral around a simple closed curve C to a double integral over the plane region D (surface in ℝ2)…
- Batch normalization In artificial neural networks, batch normalization (also known as batch norm) is a normalization technique used to make training faster and more stable…