🦉 OWL-ViT: Open-World Object Detection with Vision Transformers OWL-ViT is an open-vocabulary object detector. Github: github.com/google-…/owl_vit Paper: https://arxiv.org/abs/2205.06230 Colab: colab.research.google.com/github/…le.ipynb Dataset: https://paperswithcode.com/dataset/objects365 @ai_machinelearning_big_data