SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection

Get Started

1. Please refer to this installation guide.
2. Reproduce the results in Table 2 of our CVPR 2025 paper using the provided reference configs.

License

We release SimLTD under the permissive Apache 2.0 license. Any contributions made will also be subject to the same licensing.

Copyright 2025 LexisNexis Risk Solutions. All Rights Reserved.

Acknowledgments

We are grateful for the open-source contributions from

• PyTorch
• OpenMMLab MMDetection
• MixPL

Citation

If you find this work useful, consider citing the related paper:

@inproceedings{TranSimLTD,
  title="{SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection}",
  author={Phi Vu Tran},
  booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2025}
}