ITM threshold

Open chaochen99 opened this issue 3 years ago • 3 comments

HI, I am very fortunate to read your paper BLIP. It's very exciting.

I wonder how to set the ITM threshold when filtering?

Thanks! Looking forward to your reply.

Apr 18 '22 09:04 chaochen99

We simply set it as 0.5, thanks.

Apr 18 '22 23:04 LiJunnan1992

In train_retrieval.py, the score of ITM did not go through softmax. Did you consider using softmax at that time? When filtering, is the score of 0.5 used without softmax?

Thanks!

Apr 25 '22 03:04 chaochen99

When filtering, the score of 0.5 uses softmax?

During inference of retrieval, softmax does not affect the ranking of ITM predictions, but it does affect the relative scale w.r.t the ITC similarity. If softmax is used for ITM scores, some additional scaling on the ITC score is also needed.

Apr 25 '22 04:04 LiJunnan1992