mcahny / rovit

RO-ViT CVPR 2023 "Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers"

Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers

CVPR 2023 (Highlight) paper.

We are releasing the JAX/Flax implementation at this https URL.

@inproceedings{kim2023region,
  title={Region-aware pretraining for open-vocabulary object detection with vision transformers},
  author={Kim, Dahun and Angelova, Anelia and Kuo, Weicheng},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={11144--11154},
  year={2023}
}