Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

欢迎提意见! #6

Open
jindongwang opened this issue Apr 12, 2018 · 17 comments

Comments

Projects
None yet
8 participants
@jindongwang
Copy link
Owner

commented Apr 12, 2018

由于作者水平有限,错误、不足之处请多提意见!
如果有任何建议(新方法、新数据、新竞赛等任何新的东西),也欢迎到这里留言!

@zhenni

This comment has been minimized.

Copy link

commented Apr 19, 2018

Why not write a survey ><

@jindongwang

This comment has been minimized.

Copy link
Owner Author

commented Apr 20, 2018

@zhenni 现在的survey就有很多了,再写一个没什么用

@haoguosheng

This comment has been minimized.

Copy link

commented Apr 22, 2018

4.1.1小节最后一行“却并给出...”,是否应当是"却并未给出..."?

@jindongwang

This comment has been minimized.

Copy link
Owner Author

commented Apr 22, 2018

@haoguosheng 这个在开发版本中已修正

@zhangjiantianyasmile

This comment has been minimized.

Copy link

commented Apr 25, 2018

你好,《迁移学习简明手册》 13.4 2. 人脸识别图像数据集 这一小节中 “...按照不同的关照和曝光条件随机选出。“ 应该是 “...光照和曝光条件...” 吧?

@jindongwang

This comment has been minimized.

Copy link
Owner Author

commented Apr 25, 2018

@zhangjiantianyasmile 已更正,感谢!

@xpf

This comment has been minimized.

Copy link

commented May 1, 2018

你好,53页中fts = fts ./ repmat(sum(fts, 2), 1, size(fts, 2));
是否是fts = fts ./ repmat(sum(fts, 1), size(fts, 1), 1);
使用Xs = zscore(fts, 1);是否能将上句删除?谢谢解答

@jindongwang

This comment has been minimized.

Copy link
Owner Author

commented May 2, 2018

@xpf 没懂你的意思。。。

@CuthbertCai

This comment has been minimized.

Copy link

commented May 22, 2018

公式4.17中的第二个指示函数是否应该为等于1而不是等于0

@jindongwang

This comment has been minimized.

Copy link
Owner Author

commented May 22, 2018

@CuthbertCai 两个都是1,这个是没错的,区别是前面来自source,后面来自target

@CuthbertCai

This comment has been minimized.

Copy link

commented May 22, 2018

@jindongwang 可能我没有表达清楚,我的意思是第二个指示函数中是否应该是$\eta(x_i)=1$而不是$\eta(x_i)=0$,对于假设$\eta$来说来自source domain的样本应该判断为0,来自target domain的样本应该判断为1吧

@jindongwang

This comment has been minimized.

Copy link
Owner Author

commented May 22, 2018

@CuthbertCai 我看到了!现在这个公式是4.19了,我刚刚看偏了,可能咱们看的版本不一样。确实需要更正!

@yuyaxiong

This comment has been minimized.

Copy link

commented Sep 27, 2018

39页处,“简单说一下什么叫 AnB:(所有实验都是针对数据 B 来说的)将 A 网络的前 n 层拿来
并将它 frozen,剩下的 8 − n 层随机初始化,然后对 B 进行分类。”paper里面是指,剩下的8-n层随机初始化并在B上训练后,再对B进行分类。这么写读起来让人以为是用随机初始化的权重做后续的分类任务的。

@jindongwang

This comment has been minimized.

Copy link
Owner Author

commented Sep 29, 2018

@yuyaxiong 感谢指正!写的有些简单了

@bifeng

This comment has been minimized.

Copy link

commented Feb 20, 2019

您好,关于深度迁移学习中图31(page 38)的说明,该图是引用的哪篇论文?使用的什么数据集?
还有以下几点疑惑需要请教您:

  1. 目前,迁移学习主要都是深度迁移学习方法来做吗?或者深度迁移学习与传统迁移学习方法的结合?
  2. 相比传统的迁移学习方法,深度迁移学习方法主要是在哪方面进行迁移比较有优势(数据分布 or 特征 or 子空间 )?
@jindongwang

This comment has been minimized.

Copy link
Owner Author

commented Feb 20, 2019

@bifeng

This comment has been minimized.

Copy link

commented Feb 20, 2019

非常感谢解答!👍

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.