Florence: A New Foundation Model for Computer Vision
Automated visual understanding of our diverse and open world demands computer vision models to generalize well with minimal customization for specific tasks, similar to human vision. Computer vision foundation models, which are trained on diverse, large-scale dataset and can be adapted to a wide range of downstream tasks, are critical for this mission to solve real-world computer vision applications. While existing vision foundation models such as CLIP, ALIGN, and Wu Dao 2.0 focus mainly on mapping images and textual representations to a cross-modal shared representation, we introduce a new computer vision foundation model, Florence, to expand the representations from coarse (scene) to fine (object), from static (images) to dynamic (videos), and from RGB to multiple modalities (caption, depth). By incorporating universal visual-language representations from Web-scale image-text data, our Florence model can be easily adapted for various computer vision tasks, such as classification, retrieval, object detection, VQA, image caption, video retrieval and action recognition. Moreover, Florence demonstrates outstanding performance in many types of transfer learning: fully sampled fine-tuning, linear probing, few-shot transfer and zero-shot transfer for novel images and objects. All of these properties are critical for our vision foundation model to serve general purpose vision tasks. Florence achieves new state-of-the-art results in majority of 44 representative benchmarks, e.g., ImageNet-1K zero-shot classification with top-1 accuracy of 83.74 and the top-5 accuracy of 97.18, 62.4 mAP on COCO fine tuning, 80.36 on VQA, and 87.8 on Kinetics-600.
PDF AbstractCode
Spaces
Tasks
Action Classification
Action Recognition
Action Recognition In Videos
Cross-Modal Retrieval
Image Classification
object-detection
Object Detection
Retrieval
Transfer Learning
Video Retrieval
Visual Question Answering (VQA)
Zero-Shot Cross-Modal Retrieval
Zero-Shot Learning
Zero-Shot Transfer Image Classification
Zero-Shot Video Retrieval
ImageNet
MS COCO
Kinetics
Visual Genome
Flickr30k
Kinetics 400
AudioSet
MSR-VTT
EuroSAT
Visual Question Answering v2.0
HowTo100M
WebVid
Kinetics-600
