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.

Sign up for GitHub

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

Jump to bottom

Review-2019.11.21-黄振航 #639

Open
ZhenhangHuang opened this issue Nov 21, 2019 · 0 comments
Open

Review-2019.11.21-黄振航 #639

ZhenhangHuang opened this issue Nov 21, 2019 · 0 comments

Comments

@ZhenhangHuang
Copy link

Airbus Ship比赛
MaskRCNN(score 0.8) PolarMask(score 0.4)
1、漏检率过高：船在图片中都是小尺度图像，polar或者fcos都是随机打点在进行维度扩展
对于大尺度目标，点落入检测区域的概率大，而对于小尺度概率很小
2、polar的置信度很低(0.3-0.4)
3、错判第二图下面检测的ship横跨两个船
4、在船只检测任务中，对FPN应该都是运用小尺度的层多，对大尺度的计算存在浪费，可以尝试看看FPN大尺度层的权重值
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@ZhenhangHuang