List your company
ResearchFormerly WizWand

Image Matching on COCO (val)

80.9Matching AccuracyCLIP
-2.319.340.962.5Jan 10, 2024
Updated 8mo ago

Evaluation results

MethodLinks
CLIPLanguage=en, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0180.90.567
Relative representationsLanguage=en, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0152.5—
QAP MatchingLanguage=en, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0151.30.646
CLIPLanguage=fr, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0150.80.477
CLIPLanguage=es, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0150.40.471
CLIPLanguage=de, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0143.50.472
CLIPLanguage=it, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0141.90.472
QAP MatchingLanguage=es, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0140.90.634
QAP MatchingLanguage=fr, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0140.30.624
QAP MatchingLanguage=pl, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.01400.642
QAP MatchingLanguage=zh, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0139.90.641
QAP MatchingLanguage=de, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0139.70.627
QAP MatchingLanguage=tr, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0138.90.624
QAP MatchingLanguage=it, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0138.70.638
QAP MatchingLanguage=Avg., Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0138.7—
Relative representationsLanguage=es, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0137.8—
Relative representationsLanguage=fr, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0137.5—
Relative representationsLanguage=it, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0137.2—
Relative representationsLanguage=pl, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0136.6—
Relative representationsLanguage=zh, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0136.5—
Relative representationsLanguage=Avg., Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0136.3—
Relative representationsLanguage=tr, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0135.8—
Relative representationsLanguage=de, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0135—
QAP MatchingLanguage=ru, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0134.80.632
Relative representationsLanguage=ru, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0131.8—
QAP MatchingLanguage=ko, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0131.30.62
Relative representationsLanguage=ko, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0130.4—
QAP MatchingLanguage=jp, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0130.20.598
Relative representationsLanguage=jp, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0128.3—
CLIPLanguage=Avg., Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0127.4—
Linear regressionLanguage=en, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0125.6—
Linear regressionLanguage=pl, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0121—
Linear regressionLanguage=es, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0119.7—
Linear regressionLanguage=it, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0119.7—
Linear regressionLanguage=de, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0119.3—
Linear regressionLanguage=zh, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0119.2—
Linear regressionLanguage=Avg., Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0118.9—
Linear regressionLanguage=fr, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0118.8—
Linear regressionLanguage=tr, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0118.7—
Linear regressionLanguage=ru, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0116.3—
Linear regressionLanguage=ko, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0115.3—
Linear regressionLanguage=jp, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0115.2—
CLIPLanguage=jp, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.0112.90.337
CLIPLanguage=pl, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.018.10.261
CLIPLanguage=tr, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.017.80.301
CLIPLanguage=zh, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.012.40.133
CLIPLanguage=ru, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.011.70.077
CLIPLanguage=ko, Vision Model=CLIP ViT-L, Text Model=paraphrase-multilingual-mpnet-base-v22024.010.90.154