search

VQAssessment / FAST-VQA-and-FasterVQA

[ECCV2022, TPAMI2023] FAST-VQA, and its extended version FasterVQA.
https://www.ecva.net/papers/eccv_2022/papers_ECCV/html/1225_ECCV_2022_paper.php
Other
248 stars 25 forks source link

Match constraint #33

Closed h4nwei closed 1 year ago

h4nwei commented 1 year ago

Hi @teowu

Thanks for the interesting work. I have some questions regarding the match constraint:

  1. Is the implementation of the match constraint the same as the PatchMerching?
  2. How to perform the ablation study on mis-matched mini-cubes?

Thanks for any help you can provide.

Hanwei Best

teowu commented 1 year ago

Hi Dr Han:

Thank you for your interest.

I think it can be understood in an inverted way: the Patch Merging of Swin comes first, and then we design the fragments to make sure the merging only happens inside our mini-patches, rather than across them. And in general, the Patch Merging can be seen as a pooling layer with stride and kernel both at (2,2), so we call it a pooling layer (a special one, though, that can be matched) in our paper.

To perform ablation study, we simple modify the hyper-parameters during the sampling to make them not aligned.

Hope this can help.

Best, Haoning

h4nwei commented 1 year ago

Hi @teowu ,

Thanks for solving my puzzle on the match constraint.

Best, Hanwei