-
Notifications
You must be signed in to change notification settings - Fork 55
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
Question about RPN #17
Comments
Hi, Great question! You are correct. We did not handle this issue in our work. We tried a few ideas including dataset-specific RPN, class-specific RPN, and ignoring high confident losses in RPN. All of them did not improve or improved minor. My hypothesis is that RPNs are robust enough to generalize even if they are not trained consistently, given that we used an over-sufficient number of proposals at testing (1K proposals per image). You can find more discussions about RPN generalization in Appendix A of our Detic project. Best, |
Hello, I am very interested in your work, but I have a question to ask you. In the RPN stage, a proposal may be a positive sample in dataset A but a negative sample in dataset B. Will this produce ambiguity? Thanks!
The text was updated successfully, but these errors were encountered: