Predicting and explaining performance and diversity of neural network architecture for semantic segmentation.
John Brandon Graham-KnightCorey BondHomayoun NajjaranYves LucetPatricia LasserrePublished in: Expert Syst. Appl. (2023)
Keyphrases
- semantic segmentation
- street scenes
- conditional random fields
- superpixels
- label transfer
- weakly supervised
- scene classification
- pascal voc
- object categories
- object class
- object classes
- object detection
- image understanding
- image set
- pixel level
- segmentation algorithm
- multiscale
- biologically inspired
- natural images
- text mining
- multi class
- hidden markov models
- active learning
- feature space