Thanks for your work! In paper, bevfusion can get 0.40 with mask-modal strategy when LiDAR sensor missing. But I added "ModalMask3D" to bevfusion and trained with mask-modal strategy, the result only is 0.25. Can you provide more technology details or point out my some error operations?
Thanks for your work! In paper, bevfusion can get 0.40 with mask-modal strategy when LiDAR sensor missing. But I added "ModalMask3D" to bevfusion and trained with mask-modal strategy, the result only is 0.25. Can you provide more technology details or point out my some error operations?
Originally posted by @dingmiaomiao in https://github.com/junjie18/CMT/issues/93#issuecomment-2024643735