HyperAI
StartseiteNeuigkeitenNeueste ForschungsarbeitenTutorialsDatensätzeWikiSOTALLM-ModelleGPU-RanglisteVeranstaltungen
Suche
Über
HyperAI

Image Captioning On Whoops

Metriken

BLEU-4
CIDEr

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname
BLEU-4
CIDEr
Paper TitleRepository
OFA Large00Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images-
BLIP2 FlanT5-XXL (Fine-tuned)42177Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images-
CoCa ViT-L-14 MSCOCO25102Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images-
BLIP2 FlanT5-XXL (Zero-Shot)31120Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images-
BLIP Large1365Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images-
BLIP2 FlanT5-XL (Fine-tuned)41174Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images-
0 of 6 row(s) selected.