-
Notifications
You must be signed in to change notification settings - Fork 251
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
关于论文损失函数的一些疑问 #16
Comments
1) 这些图是手动设置的前背景的概率,然后计算出来的loss, 并不是实际网络生成的概率图计算的,是示意图。
2)SSIM的加入是受到了图像评估算法的启发,理论上你可以认为SSIM基于patch的计算方式有利于局部信息的保存,这个很难用严谨的数学方法证明。当然,你也可以认为是试出来的,其实就是trial
and error。不过话说回来,即使不是深度学习,很多算法的设计也是基于某一假设,然后不断尝试迭代出来的局部最优方案。
…On Tue, Oct 1, 2019 at 2:44 AM lipengqian ***@***.***> wrote:
尊敬的作者您好,
我认为您在论文中关于损失函数的分析相当的精彩。但是我有几个疑问:1)这些展示图是如何制作出来的?(个人猜测是保存不同训练阶段的模型,处理同一幅图片,然后可视化三个loss)
2)为什么SSIM对边缘的不一致很敏感?根据图片展示确实如此,有理论上的解释吗?(其实本质问题是我想知道您的hybrid
loss是理论指导设计还是实验指导设计的。)
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#16>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/ADSGOROMKH5WIPUVDSE7PZDQMMEXNANCNFSM4I4GNG5Q>
.
--
Xuebin Qin
PhD Candidate
Department of Computing Science
University of Alberta, Edmonton, AB, Canada
Homepage:https://webdocs.cs.ualberta.ca/~xuebin/
|
作者您好,手动设置的前背景的概率指的是什么啊 |
我想问一下 im_aug 和 gt_aug能公布一下吗 |
yes, as we described in the caption of figure 5.
…On Thu, Dec 30, 2021 at 6:24 AM Uhall ***@***.***> wrote:
1. 这些图是手动设置的前背景的概率,然后计算出来的loss, 并不是实际网络生成的概率图计算的,是示意图。
2)SSIM的加入是受到了图像评估算法的启发,理论上你可以认为SSIM基于patch的计算方式有利于局部信息的保存,这个很难用严谨的数学方法证明。当然,你也可以认为是试出来的,其实就是trial
and error。不过话说回来,即使不是深度学习,很多算法的设计也是基于某一假设,然后不断尝试迭代出来的局部最优方案。
… <#m_-6553839103826737514_>
On Tue, Oct 1, 2019 at 2:44 AM lipengqian *@*.***> wrote: 尊敬的作者您好,
我认为您在论文中关于损失函数的分析相当的精彩。但是我有几个疑问:1)这些展示图是如何制作出来的?(个人猜测是保存不同训练阶段的模型,处理同一幅图片,然后可视化三个loss)
2)为什么SSIM对边缘的不一致很敏感?根据图片展示确实如此,有理论上的解释吗?(其实本质问题是我想知道您的hybrid
loss是理论指导设计还是实验指导设计的。) — You are receiving this because you are subscribed
to this thread. Reply to this email directly, view it on GitHub <#16
<#16>>, or mute the thread
https://github.com/notifications/unsubscribe-auth/ADSGOROMKH5WIPUVDSE7PZDQMMEXNANCNFSM4I4GNG5Q
.
-- Xuebin Qin PhD Candidate Department of Computing Science University
of Alberta, Edmonton, AB, Canada Homepage:
https://webdocs.cs.ualberta.ca/~xuebin/
作者你好,基于你的解释,我认为你图5是不是都是预测前景的概率,P_fg是真值前景区域你设的显著性区域概率,P_bg是真值背景区域你设的显著性区域概率呢?
—
Reply to this email directly, view it on GitHub
<#16 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ADSGORKGKPVAYJWOLJWYG2DUTO7EBANCNFSM4I4GNG5Q>
.
Triage notifications on the go with GitHub Mobile for iOS
<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675>
or Android
<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.
You are receiving this because you commented.Message ID:
***@***.***>
--
Xuebin Qin
PhD
Department of Computing Science
University of Alberta, Edmonton, AB, Canada
Homepage: https://xuebinqin.github.io/
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
尊敬的作者您好,
我认为您在论文中关于损失函数的分析相当的精彩。但是我有几个疑问:1)这些展示图是如何制作出来的?(个人猜测是保存不同训练阶段的模型,处理同一幅图片,然后可视化三个loss)
2)为什么SSIM对边缘的不一致很敏感?根据图片展示确实如此,有理论上的解释吗?(其实本质问题是我想知道您的hybrid loss是理论指导设计还是实验指导设计的。)
The text was updated successfully, but these errors were encountered: