-
Notifications
You must be signed in to change notification settings - Fork 46
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
[OSPP] Proposal for Unknown Task Recognition Algorithm Reproduction based on Lifelong Learning of Ianvs #41
Conversation
Signed-off-by: Frank-lilinjie <lilinjie@bupt.edu.cn>
Signed-off-by: Frank-lilinjie <lilinjie@bupt.edu.cn>
Signed-off-by: Frank-lilinjie <lilinjie@bupt.edu.cn>
1. Reproducing the algorithm from the CVPR2021 paper "Learning placeholders for open-set recognition". | ||
2. Achieving an accuracy of 0.9 for unknown task recognition. | ||
3. Making unknown category recognition modules according to Ianvs architecture and contextual relationship to store in the lib library, so that the algorithm can be used on demand. | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add test report in goals #26 (comment)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Received and completed it.
Signed-off-by: Frank-lilinjie <lilinjie@bupt.edu.cn>
Signed-off-by: Frank-lilinjie <lilinjie@bupt.edu.cn>
Signed-off-by: Frank-lilinjie <lilinjie@bupt.edu.cn>
/lgtm |
The PR is perfect, but there are some minor issues about git commit convention that should be noted. For commit history of Ianvs repository more readable and cleaner, I suggest to squash the commits by More details can be refered as following:
these are just some examples, you can write it according to your commit content. |
[OSPP] Proposal for Unknown Task Recognition Algorithm Reproduction based on Lifelong Learning of Ianvs
Proposal for Unknown Task Recognition Algorithm Reproduction based on Lifelong Learning of Ianvs.
This PR is a proposal that project aims to reproduce the CVPR2021 paper "Learning placeholders for open-set recognition" in the Semantic Segmentation dataset. This paper proposes placeholders that imitate the emergence of new classes, thus helping to transform closed-set training into open-set training.
This PR is a modification of the last PR