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 smallest model in literature while performing similar to or better than other larger models on representative test sets. The efficient deep image compression model is significantly smaller than any other model in literature and performs similarly in both computational cost and reconstruction quality to the JPEG standard.
| Identifer | oai:union.ndltd.org:unt.edu/info:ark/67531/metadc1986970 |
| Date | 08 1900 |
| Creators | Chiapputo, Nicholas J. |
| Contributors | Bailey, Colleen P, Guturu, Parthasarathy, Namuduri, Kamesh |
| Publisher | University of North Texas |
| Source Sets | University of North Texas |
| Language | English |
| Detected Language | English |
| Type | Thesis or Dissertation |
| Format | Text |
| Rights | Public, Chiapputo, Nicholas J., Copyright, Copyright is held by the author, unless otherwise noted. All rights Reserved. |
Page generated in 0.002 seconds