Microsoft’s ‘Florence’ General-Purpose Foundation Model Achieves SOTA Results on Dozens of CV Benchmarks
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-scal...
Source: syncedreview.com
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.