Reliability in Semantic Segmentation: Can We Use Synthetic Data?
Thibaut LoiseauTuan-Hung VuMickaël ChenPatrick PérezMatthieu CordPublished in: CoRR (2023)
Keyphrases
- synthetic data
- semantic segmentation
- street scenes
- conditional random fields
- label transfer
- scene classification
- weakly supervised
- superpixels
- real world
- real image data
- data sets
- object categories
- object classes
- object class
- pascal voc
- image set
- image understanding
- visual words
- object detection
- higher order
- image features
- probabilistic model