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

Great work but Threshold Encoder module is useless.Details look at the picture #24

Open
lab-gpu opened this issue Oct 11, 2021 · 3 comments

Comments

@lab-gpu
Copy link

lab-gpu commented Oct 11, 2021

Thanks for the author's work.Great work!!!!!
1:Working so hard to train the Threshold Encoder which aim is to seperate the pred_map(the output of the network) to 1 or 0, but there is little differences between the pred_map after processed by the Threshold Encoder and the pred_map without processed by the Threshold Encoder.Details can look at the picture
微信图片_20211011153600
微信图片_20211011153606
微信图片_20211011153613

@lab-gpu
Copy link
Author

lab-gpu commented Oct 11, 2021

Just supress a little noise in the background.Theses noise may not influence the result of crowd counting.Pred_map is so pretty good that the TE Module play a trivial module

@lab-gpu
Copy link
Author

lab-gpu commented Oct 11, 2021

受不了了,说中文吧,你看第一张图片,预测到pred_map其实绝大部分,在目标区域已经是1,背景区域已经是0了,这是因为pred_map训练的时候,已经和mask_gt做了训练,那么训练出来的pred_map其实和mask_gt已经很接近了,我觉得通过TE(Threshold Encoder)模块,抑制掉的背景,其实真真真很少啊,不过可能这就是最后精度提升的原因吧

@taohan10200
Copy link
Owner

你好,TE的主要目的不是去除背景,就像你说的,如果训练得好,背景区域基本已经没有噪声了,这种场景自然不需要TE。TE最主要的是想减少粘连的区域,例如,对于密集粘连区域,我们希望学出来的的阈值能够自适应的在这一块区域变大来实现更好的分割。

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