Please refer to the documentation 📚 for more details. Our toolbox is similar to cocoapi in style.

Here is a quick example of how to use $D^3$.

from d_cube import D3
d3 = D3(IMG_ROOT, PKL_ANNO_PATH)
all_img_ids = d3.get_img_ids()  # get the image ids in the dataset
all_img_info = d3.load_imgs(all_img_ids)  # load images by passing a list of some image ids
img_path = all_img_info[0]["file_name"]  # obtain one image path so you can load it and inference

Some frequently asked questions are answered in this Q&A file.

Citation

If you use our $D^3$ dataset, this toolbox, or otherwise find our work valuable, please cite our paper:

@inproceedings{xie2023DOD,
  title={Described Object Detection: Liberating Object Detection with Flexible Expressions},
  author={Xie, Chi and Zhang, Zhao and Wu, Yixuan and Zhu, Feng and Zhao, Rui and Liang, Shuang},
  booktitle={Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS)},
  year={2023}
}

@inproceedings{wu2023gres,
  title={Advancing Referring Expression Segmentation Beyond Single Image},
  author={Wu, Yixuan and Zhang, Zhao and Xie, Chi and Zhu, Feng and Zhao, Rui},
  booktitle={International Conference on Computer Vision (ICCV)},
  year={2023}
}

More works related to Described Object Detection are tracked in this list: awesome-described-object-detection.