@inproceedings{2f88e7711de24787b6699690ab1d6c57,
title = "A Study on Model Compression Methods for SRGAN",
abstract = "The construction of SR algorithms by using deep learning model such as super-resolution generative adversarial networks (SRGAN) have become larger and complicated model architectures with requiring a vast amount of memory capacity. However, it is difficult to operate deep learning models which have millions of parameters at the mobile devices. Thus, in this paper, we present a study on lightweight neural network using network pruning method. Through our extensive experiments, pruned network can show similar performance to the original SRGAN model with substantially reduced model size.",
keywords = "Deep learning, Fine-tuning, Knowledge-distillation, Lightweight neural network, Network compression, Network pruning, Super-resolution",
author = "Kim, {Dong Hwi} and Lee, {Jun Won} and Park, {Sang Hyo}",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022 ; Conference date: 06-02-2022 Through 09-02-2022",
year = "2022",
doi = "10.1109/ICEIC54506.2022.9748707",
language = "English",
series = "2022 International Conference on Electronics, Information, and Communication, ICEIC 2022",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2022 International Conference on Electronics, Information, and Communication, ICEIC 2022",
address = "United States",
}