How to reproduce the result of Faster R-CNN in Table 2

Jacobi93 / Alpha-IoU

[NeurIPS 2021] Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression

GNU General Public License v3.0

154 stars 21 forks source link

How to reproduce the result of Faster R-CNN in Table 2 #8

Closed tuz95 closed 2 years ago

Jacobi93 commented 2 years ago

Thx for your interest. As mentioned in the caption of table 2 and the appendix B.1 in the paper, the results can be reproduced by changing the loss of Faster R-CNN in the MMDetection toolbox and following the original code's training protocol.