Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning.
Xinyu LuoJiaming ZhangKailun YangAlina RoitbergKunyu PengRainer StiefelhagenPublished in: CoRR (2022)
Keyphrases
- meta learning
- multi source
- semantic segmentation
- inductive learning
- learning tasks
- information fusion
- data fusion
- superpixels
- decision trees
- machine learning algorithms
- model selection
- conditional random fields
- data mining
- data integration
- machine learning
- data sources
- case study
- computer vision
- multiple sources
- learning algorithm
- natural images
- database
- recommender systems
- metadata
- feature selection
- natural scenes
- databases