ADD FG-CLIP2#41886
Open
binwang777 wants to merge 4 commits into
Open
Conversation
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: auto, fgclip2 |
Member
|
Benchmark results look impressive, yes! cc @molbap @yonigozlan @NielsRogge maybe, if any of you want to handle this? |
Collaborator
|
Taking a look! |
Author
|
@molbap @Rocketknight1 Hello, may I ask how much longer the code review will take? Could you please give us some suggestions? Thank you for your time. This is our GitHub link: (https://github.com/360CVGroup/FG-CLIP) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
FG-CLIP2 is a new generation of text-image cross-modal model excels in fine-grained discrimination and embedding. It is the foundation model for fine-grained vision-language understanding in both English and Chinese.
Across 29 datasets and 8 diverse tasks, it consistently surpasses recent strong baselines such as SigLIP 2 and MetaCLIP 2, achieving the best reported performance to date in both languages.
Merge the model from https://github.com/binwang777/transformers/tree/fgclip2