Model and demo coming soon! All things would be ready on July 20th. Stay tuned.

GAIA-det is a open source object detection toolbox that helps you with your customized AI solutions. It is built on top of gaiavision and mmdet. This repo includes a re-implementation of our CVPR2021 paper: GAIA: A Transfer Learning System of Object Detection that Fits Your Needs.

It provides functionalities that help the customization of AI solutions.

• Design customized search space of any type with little efforts.
• Manage models in search space according to your rules.
• Integrate datasets of various sources.

• Install gaiavision.
• Install mmdet.
• Install gaiadet:

git clone https://github.com/GAIA-vision/GAIA-det . && cd GAIA-det
pip install -r requirements.txt
pip install -e .

We compare our results with ResNet50 of 4x on COCO for fairness, because COCO data has been used for 3x during upstream training.

Methods denote Deformable Convolution and Cascaded Head.

FLOPS of all models are around 139GFLOPS, and the metric used above is AP50.

Please refer to DATA_PREPARATION.

Please refer to USAGE for generic use.

If you like our work and use the code or models for your research or project, please star our repo and cite our work as follows.

@InProceedings{Bu_2021_CVPR,
    author    = {Bu, Xingyuan and Peng, Junran and Yan, Junjie and Tan, Tieniu and Zhang, Zhaoxiang},
    title     = {GAIA: A Transfer Learning System of Object Detection That Fits Your Needs},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {274-283}
}