Home

/nvlabs/ MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training

Code Link
https://github.com/nvlabs/minvis
Description
By only training a query-based image instance segmentation model, MinVIS outperforms the previous best result on the challenging Occluded VIS dataset by over 10% AP. Code: https://github.com/nvlabs/minvis
Retrieved
2022/08/04
Stars
54
TOP