Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentation.
Kai HuangFeigege WangYe XiYutao GaoPublished in: CoRR (2023)
Keyphrases
- kernel learning
- semantic segmentation
- superpixels
- conditional random fields
- weakly supervised
- semi supervised
- scene classification
- dimensionality reduction
- bounding box
- object categories
- multiscale
- video sequences
- object class
- distance metric
- video data
- object classes
- data sets
- object detection
- image sequences
- image representation
- generative model
- graphical models
- pairwise