wjn922 / ReferFormer

[CVPR2022] Official Implementation of ReferFormer
Apache License 2.0
322 stars 25 forks source link

Vision Language Early fusion #37

Open nero1342 opened 1 year ago

nero1342 commented 1 year ago

I saw that you did not mention anything about the early-fusion module that you used in your paper. However, in your code, that module is utilized before the Transformer module. I think this simple module contributes a lot to the result. Can you explain about this?

Thank you!

https://github.com/wjn922/ReferFormer/blob/9c8f237adc260c512a1c5ecfc7aee81b8282649a/models/referformer.py#L141 https://github.com/wjn922/ReferFormer/blob/9c8f237adc260c512a1c5ecfc7aee81b8282649a/models/referformer.py#L243

basavaraj-hampiholi commented 1 year ago

@nero1342 I hope this is helpful for you. https://github.com/wjn922/ReferFormer/issues/27