mmaaz60 / mvits_for_class_agnostic_od

[ECCV'22] Official repository of paper titled "Class-agnostic Object Detection with Multi-modal Transformer".
MIT License
299 stars 24 forks source link

Which checkpoint to use to reproduce Object Centric OVD results? #22

Closed alexey-chaykin closed 1 year ago

alexey-chaykin commented 1 year ago

Thank you for sharing your work. Could you please clarify the name of the checkpoint to be used for regions gathering for OC-OVD?

mmaaz60 commented 1 year ago

Hi @alexey-chaykin,

Thank you for your interest in our work. We use MDef_DETR_r101_epoch20.pth checkpoints for generating regions for OVD. Note that this is the same model with name as MAVL in our paper. Please let me know if you have any questions. Thanks

alexey-chaykin commented 1 year ago

Thanks