List your company

Image-to-Text Retrieval on SV-1k

98.7R@1Smart-CLIP
69.47677.06384.6592.237Dec 4, 2024Feb 4, 2025Apr 8, 2025Jun 9, 2025Aug 11, 2025Oct 12, 2025Dec 14, 2025

Evaluation results

MethodLinks
Smart-CLIPData=WIT-400M + ShareGPT4V-1M2025.1298.7
TULIPData=WIT-400M + ShareGPT4V-1M2025.1298.6
FLAIRData=30M, Zero-shot=true, Vision Encoder=ViT-B/162024.1298.5
FLAIRData=DreamLIP 30M2025.1298.5
FLAIRData=15M, Zero-shot=true, Vision Encoder=ViT-B/162024.1297.4
FG-CLIP (w/ hard negatives)Data=WIT-400M + LAION-1.6B + GRIT-12M + 40M reg. + 10M hard negatives2025.1296.7
FLAIRData=12M, Zero-shot=true, Vision Encoder=ViT-B/162024.1296.1
LoTLIPData=100M, Zero-shot=true, Vision Encoder=ViT-B/162024.1295.5
LoTLIPData=Mixed-100M2025.1295.5
Long-CLIPData=WIT-400M + ShareGPT4V-1M2025.1294.7
β-CLIP (BCE)Data=WIT-400M + ShareGPT4V-1M, Objective=BCE2025.1294.1
β-CLIP (CE)Data=WIT-400M + ShareGPT4V-1M, Objective=CE2025.1294
FLAIRData=3M, Zero-shot=true, Vision Encoder=ViT-B/162024.1291
FineLIPData=WIT-400M + ShareGPT4V-1M2025.1290.7
Long-CLIPData=400M, Zero-shot=true, Vision Encoder=ViT-B/162024.1290.6
EVA-CLIPData=Merged-2B2025.1290.5
OpenCLIPData=2B, Zero-shot=true, Vision Encoder=ViT-B/162024.1290.3
ALIGNData=700M, Zero-shot=true, Vision Encoder=ViT-B/162024.1286.3
LiTData=100M, Zero-shot=true, Vision Encoder=ViT-B/162024.1286
SigLIPData=10B, Zero-shot=true, Vision Encoder=ViT-B/162024.1285.8
SigLIPData=WebLI-1B2025.1285.8
CLIPData=WIT-400M2025.1278.2
Fine-CLIPData=CC2.5M + 10.4M reg.2025.1270.6