Get away from Style: Category-Guided Domain Adaptation for Semantic Segmentation.
Yantian LuoZhiming WangDanlan HuangNing GeJianhua LuPublished in: CoRR (2021)
Keyphrases
- domain adaptation
- semantic segmentation
- object categories
- object detection
- object recognition
- superpixels
- object classes
- cross domain
- conditional random fields
- multiple sources
- labeled data
- training examples
- semi supervised
- scene classification
- object class
- transfer learning
- generative model
- visual words
- unlabeled data
- semi supervised learning
- sentiment classification
- image features
- computer vision
- target domain
- image annotation
- training data