Wetectron is a software system that implements state-of-the-art weakly-supervised object detection algorithms.

Check INSTALL.md for installation instructions.

The simulated partial labels (points and scribbles) of COCO can be found at Google-drive or Dropbox.

Please check tools/vis_partial_labels.ipynb for a visualization example.

Check MODEL_ZOO.md for detailed instructions.

Check GETTING_STARTED for detailed instrunctions.

If you want to run on your own dataset or use other pre-computed proposals (e.g., Edge Boxes), please check USE_YOUR_OWN_DATA for some tips.

Please also check the documentation of maskrcnn-benchmark for things like abstractions and troubleshooting. If your issues are not present there, feel free to open a new issue.

1. Sequential back-prop and ResNet models.

Please consider citing following papers in your publications if they help your research.

@inproceedings{ren-cvpr020,
  title = {Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection},
  author = {Zhongzheng Ren and Zhiding Yu and Xiaodong Yang and Ming-Yu Liu and Yong Jae Lee and Alexander G. Schwing and Jan Kautz},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020}
}
@inproceedings{ren-eccv2020,
  title = {UFO$^2$: A Unified Framework towards Omni-supervised Object Detection},
  author = {Zhongzheng Ren and Zhiding Yu and Xiaodong Yang and Ming-Yu Liu and Alexander G. Schwing and Jan Kautz},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2020}
}

This code is released under the Nvidia Source Code License.

This project is built upon maskrcnn-benchmark, which is released under MIT License.