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

与其他anchor free方法比较,如FCOS? #35

Open
wzan0001 opened this issue Sep 21, 2020 · 0 comments
Open

与其他anchor free方法比较,如FCOS? #35

wzan0001 opened this issue Sep 21, 2020 · 0 comments

Comments

@wzan0001
Copy link

不知道我理解的对不对,感觉类似centernet与FCOS的结合改进。
1.centernet方法改进来获得中心点,与centernet相比使用了椭圆区域的更多像素作为正样本中心点,这一点与FCOS使用box内的所有像素很类似,但正样本比FCOS的正样本更有效,因为更接近中心。
2.尺寸预测中使用了另一个高斯核,同样,高斯核内比centernet拥有了更多的正样本。而高斯核外尺寸回归的准确率较低故作为负样本。这里的高斯核又很类似于FCOS中的center-ness的作用,将远离中心的尺寸回归置信度降低。直接使用高斯核是否比FCOS去预测center-ness效率要高很多?
不知道理解对不对,感谢指正。

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

1 participant