Convolutional Matching Pursuit and Dictionary Training
Arthur Szlam, Koray Kavukcuoglu, and Yann LeCun
TL;DR
This paper explores convolutional matching pursuit and dictionary training, extending traditional methods like matching pursuit and K-SVD to translation-invariant settings for improved signal processing.
Contribution
It introduces convolutional matching pursuit and dictionary training methods tailored for translation-invariant applications, enhancing existing sparse coding techniques.
Findings
Effective translation-invariant sparse coding demonstrated
Improved dictionary learning performance shown
Potential applications in signal and image processing
Abstract
Matching pursuit and K-SVD is demonstrated in the translation invariant setting
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBlind Source Separation Techniques · Sparse and Compressive Sensing Techniques · Tensor decomposition and applications