Roboflow | Florence: A New Foundation for Computer Vision @Roboflow | Uploaded 2 years ago | Updated 4 hours ago
"Happy training, and well you might not even need to train any more - happy inferencing!"
Microsoft Research's Florence model sets new state of the art across a wide variety of computer vision tasks - here is how they did it and what it means for the field.
Corresponding blog:
blog.roboflow.com/florence-a-new-foundational-model-for-computer-vision
Florence paper:
arxiv.org/abs/2111.11432
Try out Clip:
blog.roboflow.com/how-to-use-openai-clip
"Happy training, and well you might not even need to train any more - happy inferencing!"
Microsoft Research's Florence model sets new state of the art across a wide variety of computer vision tasks - here is how they did it and what it means for the field.
Corresponding blog:
blog.roboflow.com/florence-a-new-foundational-model-for-computer-vision
Florence paper:
arxiv.org/abs/2111.11432
Try out Clip:
blog.roboflow.com/how-to-use-openai-clip