Single Image Super-Resolution Using Fire Modules With Asymmetric Configuration
| Autor: | Gyeonghwan Kim, Hwi Kim |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Applied Mathematics Deep learning Feature extraction 020206 networking & telecommunications 02 engineering and technology Iterative reconstruction Convolution Computer engineering Signal Processing 0202 electrical engineering electronic engineering information engineering Artificial intelligence Electrical and Electronic Engineering business Image resolution |
| Zdroj: | IEEE Signal Processing Letters. 27:516-519 |
| ISSN: | 1558-2361 1070-9908 |
| Popis: | Recently, there have been many performance improvements in super resolution using deep learning methods. However, despite the performance improvement, it remains a challenge to reduce the amount of computation for real products. In this letter, we propose a deep network that employs modified Squeezenet's fire modules. We introduce a way to modify the original fire module for effective separation of spatial- and channel-wise learning, and describe how the modified fire modules can be arranged asymmetrically for reducing the number of parameters of the network. Our experiment results show higher PSNR and competitive processing time to other super resolution networks, but with less number of parameters. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|