-
Notifications
You must be signed in to change notification settings - Fork 4
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
better name... #10
Comments
keywords that are think are interesting here:
https://namelix.com/app/?keywords=multimodal+encoder+similarity+comparator+dot+product+clip suggested there:
https://namelix.com/app/?keywords=multimodal+encoder+similarity+comparator+clip+perceptor
my ideas:
I kind of think dual-encoder might be good Ok I'll leave that here, maybe that gives ideas agreed that Multi-Modal-Comparators is a bit long |
problem of mmc is it's not googleable, you can't find it in google maybe multimodal-comparators ? |
yeah, it's an improvement
I guess... you'd think the same would be true for "timm" but they don't seem to have a problem there. maybe "python mmc" will pull this up if it ends up becoming more popular one thing I like about "mmc" is the simplicity of
the reason I didn't go this route to begin with is that I didn't want to constrain this library to just CLIP models. Maybe that was over-ambitious or a pre-mature optimization? |
maybe we could do some sort of riff on "multimodality" in general? Maybe something to do with synaesthesia? (speaking of making it a spelling challenge..)
...not a huge fan of any of these lol |
crossmodal seems pretty good. nothing seems to be called that way |
but yeah maybe just mmc |
One Perceptor To RulE Them All - OPTETA Or something like that |
"mmc" is fine, "multi-modal comparators" is awful. Maybe "zero-shot classifiers?" zsc is nice and memorable
The text was updated successfully, but these errors were encountered: