search

penghu-cs / MRL

Learning Cross-Modal Retrieval with Noisy Labels (CVPR 2021, PyTorch Code)
MIT License
50 stars 9 forks source link

top@k precision-recall curve #6

Closed zhangjiwei-japan closed 2 years ago

zhangjiwei-japan commented 2 years ago

Hi, I have some questions in your other paper, How to plot a top@k precision-recall curve(e.g,.apply CCA or DCCA method)？ thanks

penghu-cs commented 2 years ago

Thanks for your attention. You could utilize these methods to learn representations. Then the similarity/distance computed from the representations is exploited to calculate the precision-recall curve. You could refer to the code of "calcPreRecRadiusLabel.m " in https://github.com/jiangqy/DCMH-CVPR2017.git.