the rebuttal, we incorporated aLRP Loss into the "mmdetection framework", which includes the implementations of all

We thank all the reviewers for their valuable feedback. To summarize, we received three "Good Paper; accept" and a "Marginally above the acceptance threshold" ratings, which confirm the significance of our work for the community. " The experiment is only done for one method... " However, these results are not final because we used RetinaNet's optimal learning rate and schedule, which we will Our experiments are still in progress for two-stage detectors and other one-stage detectors. " ...I wonder how these label-assign strategies work with the aLRP loss. Can they be further improved? Table A2 shows that aLRP Loss and A TSS [B] are complementary. Furthermore, we notice that A TSS decreases training time of aLRP Loss by using fewer anchors (i.e. " ... the unified confidence for each anchor should have been modeling in FreeAnchor .