Parameterized deformation sparse coding via tree-structured parameter search

Brandon Burdge, Kenneth Kreutz-Delgado, Joseph Murray
2010 2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers  
Representing transformation invariances in data is known to be valuable in many domains. We consider a method by which prior knowledge about the structure of such invariances can be exploited using a novel algorithm for sparse coding across a learned dictionary of atoms combined with a parameterized deformation function that captures invariant structure. We demonstrate the value of this on both reconstructing signals, as well as improved unsupervised grouping based on invariant sparse representations. 978-1-4244-9721-8/10/$26.00
doi:10.1109/acssc.2010.5757904 fatcat:xlojbm3fxng73fzjnxztgisfga