Distill-SODA: Distilling Self-Supervised Vision Transformer for Source-Free Open-Set Domain Adaptation in Computational Pathology.
Guillaume VrayDevavrat TomarBehzad BozorgtabarJean-Philippe ThiranPublished in: IEEE Trans. Medical Imaging (2024)
Keyphrases
- domain adaptation
- multiple sources
- target domain
- source domain
- cross domain
- labeled data
- semi supervised learning
- transfer learning
- unlabeled data
- semi supervised
- computer vision
- training data
- test data
- sentiment classification
- manifold alignment
- source and target domains
- co training
- training set
- reinforcement learning