CompUDA: Compositional Unsupervised Domain Adaptation for Semantic Segmentation Under Adverse Conditions.
Ziqiang ZhengYingshu ChenBinh-Son HuaSai-Kit YeungPublished in: IROS (2023)
Keyphrases
- semantic segmentation
- street scenes
- conditional random fields
- label transfer
- superpixels
- weakly supervised
- scene classification
- object categories
- pascal voc
- machine learning
- object classes
- keypoints
- image understanding
- action recognition
- object class
- natural images
- object detection
- active learning
- image segmentation
- image processing