Efficient Implementation of the K-SVD Algorithm using Batch Orthogonal Matching Pursuit

844 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Histograms of Sparse Codes for Object Detection (2013, background): “The batch version of the OMP algorithm [27] provides considerable speed-up by precomputing the inner products between patches and codewords.”
On Single Image Scale-Up Using Sparse-Representations (2010, methodology): “[1,2] implementation, using optimized K-SVD and OMP implementations by [21].”
Learning hierarchical sparse features for RGB-(D) object recognition (2014, background): “This allows us to dramatically reduce the total cost of orthogonal matching pursuit by pre-computing some quantities (Davis et al., 1997; Rubinstein et al., 2008; Bo et al., 2011c).”
Unsupervised Feature Learning for RGB-D Based Object Recognition (2012, background): “In our unsupervised feature learning setting, a large number of image patches share the same dictionary and the total cost of OMP can be reduced by its batch version that keeps some quantities in memory to save computational cost [12, 32, 7].”
Discriminatively Trained Sparse Code Gradients for Contour Detection (2012, methodology): “This can be efficiently done with convolution and a batch version of the OMP algorithm [24].”
Visual Domain Adaptation: A survey of recent advances (2015, methodology): “For instance, a batch orthogonal matching pursuit-based KSVD algorithm for learning dictionaries was proposed in [95].”