SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments.
Divya KothandaramanRohan ChandraDinesh ManochaPublished in: ICCVW (2021)
Keyphrases
- domain adaptation
- multiple sources
- target domain
- source domain
- cross domain
- labeled data
- transfer learning
- image segmentation
- semi supervised
- semi supervised learning
- active learning
- manifold alignment
- document classification
- training data
- test data
- training samples
- sentiment classification
- unlabeled data
- domain specific
- high dimensional