search

OML-Team / open-metric-learning

Metric learning and retrieval pipelines, models and zoo.
https://open-metric-learning.readthedocs.io/en/latest/index.html
Apache License 2.0
879 stars 61 forks source link

Differentiable version of FNMR@FMR metric to use it as loss #246

Open AlekseySh opened 1 year ago

AlekseySh commented 1 year ago

A paper for inspiration: link.

deepslug commented 9 months ago

Any updates/progress on this?

AlekseySh commented 9 months ago

@deepslug Nope, not enough resources. Do you want to try it? If so, the idea is that we want to adapt the approach from this paper and make FNMR@FMR metric differentiable.

deepslug commented 9 months ago

Unfortunately, I don't have enough resources either, but this is something I’d bring on top of my (and hopefully your) list!

AlekseySh commented 9 months ago

Got it!

deepslug commented 5 months ago

As I mentioned in my previous comment on the post, I work in the field of biometrics and am keen on seeing the differential version of FNMR@FMR as it can directly optimize the metric. Given the recent active development of OML, I wanted to add this comment to bump up the thread :)

AlekseySh commented 5 months ago

@deepslug thank you for you comment. I'd like to add that we've already implemented similar idea in OML. There is SurrogatePricisonLoss -- differentiable version of Precision metric. Experiments showed it was able to perform on SOTA level. So, it would be interesting to apply similar idea to FNMR@FMR.

Contributors are welcome!