Dragonfly: A large vision-language model with multi-resolution zoom

Re:Dragonfly: A large vision-language model with multi-resol... by achristmascarl on Thursday June 06, 2024 @03:30PM (#40601408)

For the model fine-tuned on biomedical image data, does anyone with domain knowledge know how the model's answers compare to the "Gold" answers?

[ Parent | on HN ]

Re:Dragonfly: A large vision-language model with multi-resol... by TechDebtDevin on Thursday June 06, 2024 @03:40PM (#40601504)

I don't have exact domain knowledge but I'm fairly certain this type of tech has already been employed to do some of the heavy lifting for radiologists reviewing imaging results.

[ Parent | on HN ]

Re:Dragonfly: A large vision-language model with multi-resol... by rrsp on Thursday June 06, 2024 @05:21PM (#40602566)

Both the ‘gold’ answer and the model reference a PA and AP view respectively as well as a lateral chest radiograph. The picture only contains a lateral radiograph though.

[ Parent | on HN ]

Re:Dragonfly: A large vision-language model with multi-resol... by quantumwoke on Saturday June 08, 2024 @05:54AM (#40616483)

Ranges from weird phrasing to outright incorrect. Oh well, early days

[ Parent | on HN ]