CLIP the Gap: A Single Domain Generalization Approach for Object Detection

[ Paper ]

Installation

Our code is based on Detectron2 and requires python >= 3.6

Install the required packages

pip install -r requirements.txt

Datasets

Set the environment variable DETECTRON2_DATASETS to the parent folder of the datasets

    path-to-parent-dir/
        /diverseWeather
            /daytime_clear
            /daytime_foggy
            ...
        /comic
        /watercolor
        /VOC2007
        /VOC2012 

Download Diverse Weather and Cross-Domain Datasets and place in the structure as shown.

Training

We train our models on a single A100 GPU.

    python train.py --config-file configs/diverse_weather.yaml 

    or 

    python train_voc.py --config-file configs/comic_watercolor.yaml

Weights

Download the trained weights.

Citation

@InProceedings{Vidit_2023_CVPR,
    author    = {Vidit, Vidit and Engilberge, Martin and Salzmann, Mathieu},
    title     = {CLIP the Gap: A Single Domain Generalization Approach for Object Detection},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2023},
    pages     = {3219-3229}
}