Closed ZhuoranYu closed 2 years ago
Hi,
Thanks for your great work. I just have a quick question regarding the transfer experiments. My understanding of this set of experiments is that you take a LVIS-pretrained detector (e.g, Mask R-CNN) and directly evaluate it on Pascal VOC, COCO, and Object 365. In other words, there should be no training on these datasets except LVIS. Is this a correct understanding?
If so, why do we have
proposal_file=data_root + 'proposals/rpn_r101_fpn_1x_val2017.pkl'
in the dataset definition of these three datasets. I assume the proposal file is only used to train ViLD (the knowledge distillation process).Sorry for bugging you and thanks for your help!
They are not used in the validation or transferring experiment, just for avoid running errors. Sorry for my bad coding.
Hi,
Thanks for your great work. I just have a quick question regarding the transfer experiments. My understanding of this set of experiments is that you take a LVIS-pretrained detector (e.g, Mask R-CNN) and directly evaluate it on Pascal VOC, COCO, and Object 365. In other words, there should be no training on these datasets except LVIS. Is this a correct understanding?
If so, why do we have
proposal_file=data_root + 'proposals/rpn_r101_fpn_1x_val2017.pkl'
in the dataset definition of these three datasets. I assume the proposal file is only used to train ViLD (the knowledge distillation process).Sorry for bugging you and thanks for your help!