Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentation.
Kai HuangFeigege WangYe XiYutao GaoPublished in: ICCV (2023)
Keyphrases
- semantic segmentation
- kernel learning
- superpixels
- conditional random fields
- weakly supervised
- semi supervised
- scene classification
- object categories
- bounding box
- object class
- object classes
- dimensionality reduction
- video data
- image set
- machine learning
- image sequences
- visual features
- data sets
- video sequences
- key frames
- object recognition
- distance metric
- text classification
- small number
- data points
- hidden markov models