OpenCodePapers

visual-question-answering-vqa-on-whoops

Visual Question Answering (VQA)
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeExact MatchBEMModelNameReleaseDate
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images2157BLIP2 FlanT5-XXL (Fine-tuned)2023-03-13
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images2055BLIP2 FlanT5-XL (Fine-tuned)2023-03-13
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images1555BLIP2 FlanT5-XXL (Zero-shot)2023-03-13
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images838OFA Large2023-03-13
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images639BLIP Large2023-03-13
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images424BLIP2 FlanT5-XXL (Text-only FT)2023-03-13