Compressive Image Classification using Deterministic Sensing Matrices
Sheel Shah, Kushal Kejriwal
TL;DR
This paper investigates how deterministic sensing matrices affect the accuracy of SVM classifiers in compressed sensing, providing theoretical bounds on worst-case performance.
Contribution
It offers new worst-case bounds on classification accuracy for SVMs using deterministic sensing matrices in compressed sensing.
Findings
Derived worst-case bounds on classification accuracy.
Analyzed the impact of deterministic sensing matrices on SVM performance.
Provided theoretical insights into compressed sensing classification limits.
Abstract
We look at the use of deterministic sensing matrices for compressed sensing and provide worst-case bounds on the classification accuracy of SVMs on compressively sensed data.
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
TopicsSparse and Compressive Sensing Techniques · Blind Source Separation Techniques · Photoacoustic and Ultrasonic Imaging