search

hkchengrex / Mask-Propagation

[CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code :star2:. Semi-supervised video object segmentation evaluation.
https://hkchengrex.github.io/MiVOS/
MIT License
128 stars 22 forks source link

Does the kernelized memory need training? #35

Closed zhouweii234 closed 3 years ago

zhouweii234 commented 3 years ago

I use the kernelized memory when evaluate STCN while did not use it when training. But the result showed a slight decrease. The raw J&F-Mean of davis2016val is 0.916, davis2017val is 0.853and davis2017testdev is 0.755 . After I use the kernelized memory, J&F-Mean of davis2016val is 0.913, davis2017val is 0.852 and davis2017testdev is 0.750 . Does it because the kernelized memory need training? But why it need training since it has no trainable parameters?

hkchengrex commented 3 years ago

It does not need training. It might be because KMN is implicitly solving the memory domination problem using spatial query constraint, leading to diminishing returns when used in conjunction with STCN.