-
Notifications
You must be signed in to change notification settings - Fork 8
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
Performance in correct Mask R-CNN implementation #3
Comments
@flashtek Hi, waiting for your response. |
Hi @wondervictor, Furthermore, we are not sure what you mean when you're talking about the Otherwise, please noticed also that we have shown in the paper that the performance-gain is very sensitive to the exponent Lastly, please send us a complete overview of your configuration (of the base M-RCNN and the newly added Edge Agreement Head) as well as a figure containing the loss curves (edge agreement loss, mark loss) and some samples of the predicted masks w/ and w/o the Edge Agreement Head so that we can better understand your problem. |
Thanks for your reply. I have a new understanding of your method after your explanation. I ignore the detail that magnitude is not adopted in your method. I've rechecked your code and grasped more details already. I'll fix bugs in my implementation and continue some experiments. |
Hi, thanks for your nice work and I appreciate it much.
I have some questions about your implementation. Your implementation is based on Mask_RCNN but I found this implementation might exist many problems which led to much lower performance than the official implementation(Detectron, maskrcnn-benchmark).
I'm interested in your work and try to implement your proposed method in maskrcnn-benchmark. The only difference between my implementation and yours is that I use
abs()
instead ofsqrt()
to aggregate edges detected from X-direction and Y-direction becausesqrt
will result in numerical problems.sqrt
andabs
is nearly the same in the theory.And I obtained results below and my implementation is consistent with the official implementation.
And I wonder why I can't obtain the performance gain in your paper. Can you provide results obtained from more accurate implementations?
The text was updated successfully, but these errors were encountered: