CVPR2018_Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning
http://mmlab.ie.cuhk.edu.hk/projects/RL-Restore/
强化学习的入门介绍:https://blog.csdn.net/aliceyangxi1987/article/details/73327378
https://www.zhihu.com/question/41775291
CNN在low-level的问题处理前沿:
deblurring: | S. Nah, T. H. Kim, and K. M. Lee. Deep multi-scale convolutional neural network for dynamic scene deblurring. In CVPR, 2017. |
J. Sun, W. Cao, Z. Xu, and J. Ponce. Learning a convolutional | |
L. Xu, X. Tao, and J. Jia. Inverse kernels for fast spatial | |
denoising: | Y. Chen,W. Yu, and T. Pock. On learning optimized reaction |
S. Lefkimmiatis. Non-local color image denoising with convolutional | |
Z. Wang, D. Liu, S. Chang, Q. Ling, Y. Yang, and T. S. | |
JPEG artifacts reduction: | C. Dong, Y. Deng, C. C. Loy, and X. Tang. Compression artifacts |
J. Guo and H. Chao. Building dual-domain representations | |
Z. Wang, D. Liu, S. Chang, Q. Ling, Y. Yang, and T. S. | |
super-resolution: | C. Dong, C. C. Loy, K. He, and X. Tang. Image superresolution |
T.-W. Hui, C. C. Loy, and X. Tang. Depth map superresolution | |
J. Kim, J. Kwon Lee, and K. Mu Lee. Accurate image superresolution | |
J. Kim, J. Kwon Lee, and K. Mu Lee. Deeply-recursive | |
W.-S. Lai, J.-B. Huang, N. Ahuja, and M.-H. Yang. Deep | |
Y. Tai, J. Yang, and X. Liu. Image super-resolution via deep | |
Y. Tai, J. Yang, X. Liu, and C. Xu. Memnet: A persistent | |
X. Wang, K. Yu, C. Dong, and C. C. Loy. Recovering realistic |
PSNR:
详细解释,读下面的链接:
http://www.360doc.com/content/16/0919/12/496343_591970301.shtml
独热码,在英文文献中称做 one-hot code, 直观来说就是有多少个状态就有多少比特,而且只有一个比特为1,其他全为0的一种码制,更加详细参加one_hot code(维基百科)。在机器学习中对于离散型的分类型的数据,需要对其进行数字化比如说性别这一属性,只能有男性或者女性或者其他这三种值,如何对这三个值进行数字化表达?一种简单的方式就是男性为0,女性为1,其他为2,这样做有什么问题?
长短期记忆(Long-Short Term Memory, LSTM)是一种时间递归神经网络(RNN),论文首次发表于1997年。由于独特的设计结构,LSTM适合于处理和预测时间序列中间隔和延迟非常长的重要事件。