List your company

Visual Question Answering on OK-VQA v1.1 (test)

66.1VQA ScorePaLM-E
32.362441.121249.8858.6388Sep 29, 2023

Evaluation results

MethodLinks
PaLM-EBase Model=PaLM-E (562B), Knowledge Source=PaLM-E2023.0966.1—
PALI (17B)Base Model=PALI (17B), Knowledge Source=PALI2023.0964.5—
RA-VQA-v2 (BLIP 2)Base Model=BLIP 2 (T5-XL), K=5, Knowledge Source=GoogleSearch2023.0962.0862.01
ProphetBase Model=GPT-3, Knowledge Source=GPT-32023.0961.11—
RA-VQA-v2 (BLIP 2) w/o ROIBase Model=BLIP 2 (T5-XL), K=5, Knowledge Source=GoogleSearch2023.0960.7561.63
RA-VQA-v2 (BLIP 2) w/o ROI & VEBase Model=BLIP 2 (T5-XL), K=5, Knowledge Source=GoogleSearch2023.0960.4159.95
PromptCapBase Model=GPT-3, Knowledge Source=GPT-32023.0960.4—
RA-VQA-v2 (BLIP 2) w/o ROI & Late-interactionBase Model=BLIP 2 (T5-XL), K=5, Knowledge Source=GoogleSearch, Retriever=DPR2023.0959.2160.18
RA-VQA-v2 (BLIP 2) w/o ROI & VE & Late-interactionBase Model=BLIP 2 (T5-XL), K=5, Knowledge Source=GoogleSearch, Retriever=DPR2023.0958.759.49
RA-VQA-v2 (BLIP 2) w/o Late-interactionBase Model=BLIP 2 (T5-XL), K=5, Knowledge Source=GoogleSearch, Retriever=DPR2023.0958.259
REVIVEBase Model=GPT-3, Knowledge Source=Wikipedia + GPT-32023.0958—
FlamingoBase Model=Flamingo (80B), Knowledge Source=Flamingo2023.0957.8—
PALI (15B)Base Model=PALI (15B), Knowledge Source=PALI2023.0956.5—
BLIP 2 (fine-tuned) w/o knowledgeBase Model=BLIP 2 (T5-XL)2023.0955.4459.49
RA-VQA-v2 (T5-large)Base Model=T5-large, K=5, Knowledge Source=GoogleSearch2023.0954.8558.85
RA-VQA (joint training)Base Model=T5-large, K=50, Knowledge Source=GoogleSearch2023.0954.4859.41
KAT-EnsembleBase Model=T5-large, GPT-3, K=40, Knowledge Source=Wikipedia + GPT-32023.0954.41—
PALI (3B)Base Model=PALI (3B), Knowledge Source=PALI2023.0952.4—
RA-VQA-v2 (T5-large) w/o ROI & VE & Late-interactionBase Model=T5-large, K=5, Knowledge Source=GoogleSearch, Retriever=DPR2023.0951.4555.89
RA-VQABase Model=T5-large, K=5, Knowledge Source=GoogleSearch2023.0951.2255.77
TRiG EnsembleBase Model=T5-large, K=100, Knowledge Source=Wikipedia2023.0950.554.73
PICaBase Model=GPT-3, Knowledge Source=GPT-32023.0948—
T5-large (fine-tuned) w/o knowledgeBase Model=T5-large2023.0947.5251.38
VRRK=100, Knowledge Source=GoogleSearch2023.0945.08—
KAT-T5Base Model=T5-large, K=40, Knowledge Source=Wikipedia2023.0944.25—
MAVEXKnowledge Source=Wikipedia + ConceptNet + Google Images2023.0939.4—
KRISPKnowledge Source=ConceptNet + Wikipedia2023.0938.35—
ConceptBERTKnowledge Source=ConceptNet2023.0933.66—