- [2024.2.27] Our work has been accepted to CVPR 2024 ๐
- [2024.3.1] Training and inference code released
Segment Anything Model was pre-trained on a large-scale dataset but exhibits awkward performance on diverse downstream segmentation tasks. We adapt SAM through weak supervision to enhance its generalization capabilities.
The proposed self-training architecture with anchor network regularization and contrastive loss regularization. Red arrows indicates the backpropagation flow.
- Release code
see INSTALL.
see PREPARE.
# 1 modify configs/config.py
# Prompt type: box, point, coarse
# 2 adapt
python adaptation.py
The content of this project itself is licensed under LICENSE.
If you find this project useful in your research, please consider cite:
@article{zhang2023improving,
title={Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation},
author={Zhang, Haojie and Su, Yongyi and Xu, Xun and Jia, Kui},
journal={arXiv preprint arXiv:2312.03502},
year={2023}
}