Some questions about Axial-attention about uacanet HOT 7 CLOSED

I think you are right. Thank you for letting me know. I'll keep in mind this in my future works.

from uacanet.

Okay！And thanks for your great code work, this is a very clear template！

from uacanet.

Any intention to re-train all model in this repo? @plemeri

from uacanet.

I'm not planning to since this isn't our main contribution, but thanks for letting me know that the authors of CaraNet seems to be using our code without any citation. I really feel bad about it.

from uacanet.

from uacanet.

Hello, yes i had sadly misunderstood the usage of the attention module for CaraNet. I initially thought, that they implemented the code similar, but ended up not using the axial attention, misinterpreting the inital gamma value of the self attention layer and mixing up the implementaton with the reverse attention module. It is indeed correct, that the axial attention is used by CaraNet, unreferenced in the published paper. However i think they reference that fact in the official repository.

I am sry for disturbing you with that comment and wanted to delete it, once i realized my initial assumption to be wrong.

from uacanet.

I just noticed that the author of CaraNet updated their readme.

from uacanet.