Awesome

HASSOD: Hierarchical Adaptive Self-Supervised Object Detection

This is the official PyTorch implementation of our NeurIPS 2023 paper:

HASSOD: Hierarchical Adaptive Self-Supervised Object Detection

[Project Page] [Paper-arXiv] [Paper-OpenReview] [Video-YouTube] [Video-Bilibili]

Shengcao Cao, Dhiraj Joshi, Liang-Yan Gui, Yu-Xiong Wang

🔎 Overview

HASSOD is a fully self-supervised approach for object detection and instance segmentation, demonstrating a significant improvement over the previous state-of-the-art methods by discovering a more comprehensive range of objects. Moreover, HASSOD understands the part-to-whole object composition like humans do, while previous methods cannot. Notably, we improve class-agnostic Mask AR from 20.2 to 22.5 on LVIS, and from 17.0 to 26.0 on SA-1B.

🛠️ Instructions

To use our code and reproduce the results, please follow these detailed documents step by step:

• Preparation: Prepare the environment, data, and pre-trained models
• Reproduction: Produce pseudo-labels and train the object detector (download links included for our pseudo-labels and model)
• Demo: Once the preparation is finished, you can try out the demo code and test our model on any image.

🙏 Acknowledgements

Our code is developed based on the following repositories:

• CutLER
• Unbiased Teacher
• Detectron2

We greatly appreciate their open-source work!

⚖️ License

This project is released under the Apache 2.0 license. Other codes from open source repository follows the original distributive licenses.

🌟 Citation

If you find our research interesting or use our code, data, or model in your research, please consider citing our work.

@inproceedings{cao2023hassod,
    title={{HASSOD}: Hierarchical Adaptive Self-Supervised Object Detection},
    author={Cao, Shengcao and Joshi, Dhiraj and Gui, Liangyan and Wang, Yu-Xiong},
    booktitle={NeurIPS},
    year={2023}
}