encounter1997 / fp-detr Goto Github PK

As stated in the title.

Thanks for your contribution in DETR pretraining. I do have a few questions about Figure 1. from the paper. At the fine-tuning stage, as indicated from the figure, the left part is the input patches and the right part if query content embeddings + query positional embedding. If query positional embedding act as visual prompts in this case, what exactly do you mean by "query content embeddings" and where can I find them in the figure?

My other question is that, given the assumption that identifying object regions can be understood as visual prompting, how does adding a task adaptor (modelling object relations) help in achieving better visual prompting? Is there any intuition other than the fact that it models object relations better? Thanks.

Thanks for your great works!
This work attracts my attention, and I am curious of the implementation.
I wonder when will you release the code.
Thanks.

Excuse me, do you have any plan to release codes or instructions for pretraining?