Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Bin Xiao, Haiping Wu, Weijian Xu, Xiyang Dai, Houdong Hu, Yumao Lu, Michael Zeng, Ce Liu, Lu Yuan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 4818-4829

We introduce Florence-2 a novel vision foundation model with a unified prompt-based representation for various computer vision and vision-language tasks. While existing large vision models excel in transfer learning they struggle to perform diverse tasks with simple instructions a capability that implies handling the complexity of various spatial hierarchy and semantic granularity. Florence-2 was designed to take text-prompt as task instructions and generate desirable results in text forms whether it be captioning object detection grounding or segmentation. This multi-task learning setup demands large-scale high-quality annotated data. To this end we co-developed FLD-5B that consists of 5.4 billion comprehensive visual annotations on 126 million images using an iterative strategy of automated image annotation and model refinement. We adopted a sequence-to-sequence structure to train Florence-2 to perform versatile and comprehensive vision tasks. Extensive evaluations on numerous tasks demonstrated Florence-2 to be a strong vision foundation model contender with unprecedented zero-shot and fine-tuning capabilities.