Microsoft’s ‘Florence’ General-Purpose Foundation Model Achieves SOTA Results on Dozens of CV Benchmarks

Resource

Microsoft’s ‘Florence’ General-Purpose Foundation Model Achieves SOTA Results on Dozens of CV Benchmarks

ML Model by Sandra Carrasco 2y ago

NewsResearch & Reports

https://syncedreview.com/2021/11/29/deepmind-podracer-tpu-based-rl-frameworks-deliver-exceptional-performance-at-low-cost-154/

In the paper A New Foundation Model for Computer Vision, a Microsoft research team proposes Florence, a novel foundation model for computer vision that significantly outperforms previous large-scale pretraining approaches and achieves new SOTA results across a wide range of visual and visual-linguistic benchmarks.

Resource

Microsoft’s ‘Florence’ General-Purpose Foundation Model Achieves SOTA Results on Dozens of CV Benchmarks

Attributes