Efficient Convolutional Neural Networks for Image Processing Applications
Description:
Modern machine learning techniques focus on extremely deep and multi-pathed networks, resulting in large memory and computational requirements. This thesis explores techniques for designing efficient convolutional networks including pixel shuffling, depthwise convolutions, and various activation fucntions. These techniques are then applied to two image processing domains: single-image super-resolution and image compression. The super-resolution model, TinyPSSR, is one-third the size of the next…
more
Date:
August 2022
Creator:
Chiapputo, Nicholas J.
Partner:
UNT Libraries