facebookresearch / detr

End-to-End Object Detection with Transformers
Apache License 2.0
13.08k stars 2.37k forks source link

using vit as image backbone #599

Open FightingFighting opened 10 months ago

FightingFighting commented 10 months ago

Hi,

Thank you very much for you great work.

have you tried to use ViT as image backbone? Do you thanl does that work?

best, zhi

JeavanCode commented 7 months ago

I am working on it as a research project, currently its hard to converge, I would inform you if there is any progess. If you find some other researches about this, please let me know.