hkchengrex / MiVOS

[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!
https://hkchengrex.com/MiVOS/
MIT License
469 stars 64 forks source link

Which line of your code is to achieve Memory Read with Top-k Filtering? #3

Closed longmalongma closed 3 years ago

longmalongma commented 3 years ago

Hi, thanks for your great work. Which line of your code is to achieve Memory Read with Top-k Filtering?

longmalongma commented 3 years ago

Hi, thanks for your great work. Which line of your code is to achieve Memory Read with Top-k Filtering?

Your code is used for Interactive Video Object Segmentation. If we use your code to do semi-supervised vos, what changes need to be made?

hkchengrex commented 3 years ago
  1. This line: https://github.com/hkchengrex/MiVOS/blob/b1992e6a2ecab84ff1b61f896e501cb357ee7b3d/model/propagation/prop_net.py#L54
  2. You should use Mask-Propagation. I have them labeled in the first table of the readme!
longmalongma commented 3 years ago
  1. This line: https://github.com/hkchengrex/MiVOS/blob/b1992e6a2ecab84ff1b61f896e501cb357ee7b3d/model/propagation/prop_net.py#L54
  2. You should use Mask-Propagation. I have them labeled in the first table of the readme!

Ok, I see it, thanks for your reply.