Booooooooooo/CSD
Towards Compact Single Image Super-Resolution via Contrastive Self-distillation, IJCAI21
Python
Issues
- 0
为什么不直接采用hr作为负样本?
#17 opened by tanbuzheng - 3
关于动态分配两种支路的问题
#11 opened by haodongyu - 0
- 5
baseline比较并不公平 如何验证蒸馏方法的有效性
#9 opened by billionfish - 3
Some question about speed up
#12 opened by wangqiim - 0
About Contrastive Loss
#15 opened by YangGangZhiQi - 0
请问论文中的局部子分支的参数量是如何计算得到的?
#14 opened by jchenTech - 0
vgg19_ImageNet.ckpt
#13 opened by githublei-min - 1
Is it only works on existing models, or eventually it outputs a pertained model based on a reference one?
#3 opened by roimulia2 - 0
- 2
About EDSR+ teacher performance
#8 opened by guyuchao - 3
关于baseline 0.25x
#7 opened by billionfish - 1
CL negtive sample question
#6 opened by wangqiim - 1
- 2
the code is different to the paper
#5 opened by songyonger - 1
Can you provide the full text version of the paper?? I cant find it anywhere on the internet
#2 opened by rushi-the-neural-arch - 0
Can you provide the full text version of the paper?? I cant find it anywhere on the internet
#1 opened by rushi-the-neural-arch