List your company

Text-to-Image Retrieval on Flickr

98.9R@1U-MARVEL+
-0.73225.1345176.866Jun 13, 2024Sep 29, 2024Jan 16, 2025May 4, 2025Aug 21, 2025Dec 7, 2025Mar 26, 2026

Evaluation results

MethodLinks
U-MARVEL+Reranker=true2025.0798.9——
U-MARVELReranker=false2025.0797.2——
LamRAReranker=true2025.0796.5——
UniMEReranker=false2025.0793.9——
MiCoZero-shot=false2024.0691.1——
SOTAZero-shot=false2024.0690.3——
MiCoZero-shot=true2024.0690.1——
SOTAZero-shot=true2024.0689.7——
LamRAreranking=pointwise/listwise2024.1288.1——
LamRA-RetReranker=false2025.0788.1——
VLM2VecReranker=false2025.0785.8——
SigLIP 2Setting=Zero-shot2026.0285.7——
UniIR-CLIP_SFReranker=false2025.0784.1——
E5-VReranker=false2025.0784——
EVA-CLIPparameters=18B2024.1283.3——
LamRA-Ret2024.1282.8——
VersaViTVision backbone state=Unfrozen, Projection layer fine-tuning=true, Training data alignment=30M image-text pairs2026.0282.2——
CLIP-LReranker=false2025.0781.8——
EVA-CLIPparameters=8B2024.1280.8——
EVA-CLIP-8BSetting=Zero-shot2026.0280.8——
SigLIPSetting=Zero-shot2026.0280.5——
E5-V2024.1279.5——
UniIR-CLIP2024.1278.7——
VersaViTVision backbone state=Frozen, Projection layer fine-tuning=true, Training data alignment=30M image-text pairs2026.0277——
Long-CLIP-L2024.1276.1——
ViT-B/16Architecture=ViT-B/16, Zero-shot evaluation=true2026.0375.5——
MagicLens-L2024.1272.5——
CLIP-L2024.1267.3——
CLIP-LSetting=Zero-shot2026.0265.2——
MagicLens-LReranker=false2025.0760.9——
CLIP-RDArchitecture=ViT-T/16, Zero-shot evaluation=true2026.0358.6——
TinyCLIPArchitecture=TinyCLIP, Zero-shot evaluation=true2026.0358.5——
CLIP-KD*Architecture=ViT-T/16, Zero-shot evaluation=true2026.0356.4——
ViT-T/16Architecture=ViT-T/16, Zero-shot evaluation=true2026.0342——
ItemizedCLIPEvaluation Protocol=Zero-shot, Training Data=Itemized-cc0.3M2025.1214.438.8—
FLAIREvaluation Protocol=Zero-shot, Training Data=Itemized-cc0.3M2025.1211.936.1—
DreamLIPEvaluation Protocol=Zero-shot, Training Data=Itemized-cc0.3M2025.129.630—
Multi-positive SigLIPEvaluation Protocol=Zero-shot, Training Data=Itemized-cc0.3M2025.129.230.3—
Vanilla SigLIPEvaluation Protocol=Zero-shot, Training Data=Itemized-cc0.3M2025.124.716.5—
Vanilla CLIPEvaluation Protocol=Zero-shot, Training Data=Itemized-cc0.3M2025.123.111—
CLIPArchitecture=L/142026.04——65.2
CLIP-KDBackbone=ResNet-50, Zero-shot=true2026.03——69.4
CLIP-KDBackbone=ResNet-18, Zero-shot=true2026.03——52.4
CLIP-RDBackbone=ResNet-50, Zero-shot=true2026.03——70.4
CLIP-RDBackbone=ResNet-18, Zero-shot=true2026.03——52.7
CLIP-RDBackbone=EfficientNet-B0, Zero-shot=true2026.03——62.7
DINOv2 (dino.txt)Architecture=L/142026.04——77.1
EfficientNet-B0Backbone=EfficientNet-B0, Zero-shot=true, Role=Student2026.03——47.2
OpenCLIPArchitecture=G/142026.04——79.5
PE-coreArchitecture=G/142026.04——85.7
ResNet-18Backbone=ResNet-18, Zero-shot=true, Role=Student2026.03——41.5
ResNet-50Backbone=ResNet-50, Zero-shot=true, Role=Student2026.03——52.7
SigLIP2Architecture=g/162026.04——86
TIPSArchitecture=g/142026.04——84.5
TIPSv2Architecture=g/142026.04——85.9
ViT-B/16Backbone=ViT-B/16, Zero-shot=true, Role=Teacher2026.03——75.5