List your company
ResearchFormerly WizWand

Vision-language alignment on CINIC-10

100AccuracyGADL
-4235077Sep 11, 2025
Updated 4mo ago

Evaluation results

MethodLinks
GADLVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.09100
GurobiVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.09100
Hahn-GrantVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.09100
GurobiVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.0980
Hahn-GrantVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.0980
GADLVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.0980
MPOptVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.0979
GurobiVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.0979
Hahn-GrantVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.0979
OTVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.0977.5
LocalCKAVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.0968
GADLVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.0960
LocalCKAVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.0957
GADLVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.0956.7
FAQVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.0955.5
LocalCKAVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.0952.5
GurobiVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.0950
Hahn-GrantVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.0950
OTVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.0949.5
MPOptVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.0947
GADLVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.0946
GADLVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.0942
GurobiVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.0940
Hahn-GrantVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.0940
FAQVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.0931
FAQVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.0930.5
LocalCKAVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.0930
FAQVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.0929.5
OTVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.0920
OTVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.0915.5
GurobiVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.0910
Hahn-GrantVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.0910
LocalCKAVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.094
OTVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.092
MPOptVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.090
FAQVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.090
MPOptVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.090
MPOptVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.090
LocalCKAVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.090
OTVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.090
FAQVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.090
MPOptVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.090