Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training.
Xiaofeng LiuYuzhuo HanSong BaiYi GeTianxing WangXu HanSite LiJane YouJu LuPublished in: CoRR (2020)
Keyphrases
- semantic segmentation
- street scenes
- label transfer
- conditional random fields
- superpixels
- training set
- scene classification
- weakly supervised
- pascal voc
- object categories
- object classes
- supervised learning
- training samples
- training examples
- bayesian networks
- image set
- object classification
- image understanding
- co occurrence
- d objects
- viewpoint
- multiscale