C-OWOD Combinatorial Open-World Detection

Requirements

• Linux or macOS with Python ≥ 3.8.
• Install PyTorch ≥ 1.9.0, torchvision, Detectron2, timm, and einops.
• Prepare datasets:
  • Download COCO and PASCAL VOC.
  • Convert annotation format using coco_to_voc.py.
  • Move all images to datasets/JPEGImages and annotations to datasets/Annotations.

Getting Started

• Training for open world object detection:

  bash run_owod.sh
  

  Evaluation for open world object detection:

  bash test_owod.sh
  

• Experiment for incremental object detection:

  bash run_iod.sh
  

• Visualize the results:

  python demo.py -i LIST_OF_IMAGES
  

• Note that we are using an ImageNet pre-trained backbone.

Acknowledgement

Our implementation is based on RandBox which uses Detectron2 and Sparse R-CNN.