Could you provide the checkpoint used to generate class-agnostic proposals in Object Centric OVD?
fushh opened this issue · 1 comments
In Object Centric OVD, the authors use the checkpoint trained from a subset of LMDet which has no overlap with any of the evaluation datasets. However, it seems that the checkpoint MDef_DETR_r101_epoch20.pth mentioned in Issue#22 is trained with the full dataset as it is the same checkpoint in evaluation. Thus the checkpoint used to generate class-agnostic proposals is needed to prevent leaking information. Please let me know if I missed anything. Thank you.
is the checkpoint named MDef_DETR_r101_epoch20_ore.pth? This checkpoint is trained on a filtered dataset generated by removing all captions from LMDet listing any of the 60 unknown categories evaluated in ORE. I'm curious if this will stiil include the rare classes in the LVIS dataset.