YOLO-World

• Developed by
  • Tencent AI Lab, ARC Lab, Tencent PCG, Huazhong University of Science and Technology
• Model type
  • Re-parameterizable Vision-Language Path Aggregation Network
• Task
  • Object Detection
• Model description
  • Is the next-generation of YOLO detectors, aiming for real-time open-vocabulary object detection.
  • Pre-trained on large-scale vision-language datasets, including Objects365, GQA, Flickr30K, and CC3M, which enpowers YOLO-World with strong zero-shot open-vocabulary capbility and grounding ability in images.
  • Achieves fast inference speeds and presents re-parameterization techniques for faster inference and deployment given users' vocabularies.