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

|w|的校正方式? #52

Open
medicineqian opened this issue Jun 3, 2022 · 2 comments
Open

|w|的校正方式? #52

medicineqian opened this issue Jun 3, 2022 · 2 comments

Comments

@medicineqian
Copy link

作者你好,我最近在阅读跨模态行人检测的论文,我想问一下文章中提到的|w|以什么方式来校正呢?
我看见论文中|w|也是用卷积和连接层预测的,wd和wn两个指标有损失函数校正,那么|w|怎么使它预测更准确呢?

@CalayZhou
Copy link
Owner

您好,|w|的值反应在wr与wt上,而wr与wt会对最终的置信度施加权重,所以在分类损失反向传播时时会对|w|进行优化;不过MBNet的光照加权设计得比较粗糙,有挺大的改进空间~

@medicineqian
Copy link
Author

medicineqian commented Jun 4, 2022 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants