Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training.
Xiaofeng LiuYuzhuo HanSong BaiYi GeTianxing WangXu HanSite LiJane YouJun LuPublished in: AAAI (2020)
Keyphrases
- semantic segmentation
- street scenes
- label transfer
- superpixels
- conditional random fields
- weakly supervised
- image understanding
- scene classification
- pascal voc
- training examples
- training set
- higher order
- object segmentation
- object detection
- object class
- image matching
- image segmentation
- object classes
- image features
- multiscale
- bayesian networks