Closed tuz95 closed 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.
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.