SGT: Self-Guided Transformer for Few-Shot Semantic Segmentation.
Kangkang AiHaigen HuQianwei ZhouQiu GuanPublished in: ICASSP (2024)
Keyphrases
- semantic segmentation
- street scenes
- superpixels
- conditional random fields
- scene classification
- video sequences
- label transfer
- object classes
- visual features
- weakly supervised
- pascal voc
- object categories
- key frames
- image set
- video data
- natural images
- image understanding
- biologically inspired
- object recognition
- object class
- object detection
- bag of words
- pixel level
- information extraction
- hidden markov models
- multiscale