event

Ph.D. Dissertation Defense - Lee Richert

Primary tabs

TitleMulti-Layer Dictionary Learning Using Low-Rank Updates

Committee:

Dr. David Anderson, ECE, Chair, Advisor

Dr. Mark Davenport, ECE

Dr. Justin Romberg, ECE

Dr. Ashwin Pananjady, ECE

Dr. Jacob Abernethy, CoC

Abstract: This dissertation presents a novel convolutional dictionary learning algorithm for signals with a large number of channels. The algorithm uses low-rank updates for the dictionary, so that a matrix decomposition necessary for pursuit can be updated efficiently. The novel approach is applied to multi-layer dictionary models with multi-channel dictionaries and single-channel coefficients and demonstrated on the task of JPEG compression artifact removal.

Status

  • Workflow Status:Published
  • Created By:Daniela Staiculescu
  • Created:12/01/2021
  • Modified By:Daniela Staiculescu
  • Modified:12/01/2021

Categories

Target Audience