During training phase, more connections (e.g. channel concatenation in last layer of DenseNet) means more occupied GPU memory and lower GPU utilization, requiring more training time. The increase of training time is also not conducive to launch application of SR algorithms. This's why we abandoned DenseNet as basic network. Futhermore, we abandoned this paper due to its limitation only applied on medical images. Please view our lastest work applied on general images at arXiv:1911.03464.
@article{arxiv.1906.06575,
title = {Single Image Super-resolution via Dense Blended Attention Generative Adversarial Network for Clinical Diagnosis},
author = {Kewen Liu and Yuan Ma and Hongxia Xiong and Zejun Yan and Zhijun Zhou and Chaoyang Liu and Panpan Fang and Xiaojun Li and Yalei Chen},
journal= {arXiv preprint arXiv:1906.06575},
year = {2020}
}
Comments
We abandoned this paper due to its limitation only applied on medical images, please view our lastest work at arXiv:1911.03464