An Uncertainty-guided Tiered Self-training Framework for Active Source-free Domain Adaptation in Prostate Segmentation (MICCAI 2024 Accept 🎉)

We are currently working on a more comprehensive and robust benchmark for Active Source-Free Domain Adaptation. Our goal is to provide a standardized, reliable framework to evaluate and compare methods in this growing area. The benchmark will include well-curated datasets and state-of-the-art algorithms, enabling consistent and fair assessments. The code and datasets will be released soon. Stay tuned for updates, and feel free to watch or star this repository to be notified when we release the full benchmark!