/sc-temporal-smoothing

sparse coding with temporal smoothing

Primary LanguageJupyter NotebookMIT LicenseMIT

Temporally smooth sparse coding

Architecture based on Rozell's '08 paper on a locally competitive algorithm (LCA) for Sparse Approximation: https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.64.7897&rep=rep1&type=pdf

Further inspiration is taken from current neuroscience literature

Abstract

We consider the relationship between representations of natural images in a temporally smooth sequence (i.e.consecutive frames in a video). Traditionally, sparse coding methods learn representations of images in isolation. Here, we learn an image’s sparse representation with the previous image’s representation as a starting point.

To-Do

  • Different sized dictionary elements
  • Support for RGB images
  • Support for Convolutional Sparse Coding
  • Implement same technique in other ML architectures

Collaborators: Jeff Winchell, Dr. Edward Kim (Drexel University)