Cross-Attention Vision Transformer for Few-Shot Semantic Segmentation.
Matheus Eduardo dos SantosSilvio Jamil Ferzoli GuimarãesZenilton Kleber Gonçalves do Patrocínio Jr.Published in: BigMM (2023)
Keyphrases
- semantic segmentation
- street scenes
- label transfer
- conditional random fields
- superpixels
- weakly supervised
- computer vision
- scene classification
- video sequences
- object class
- vision system
- object categories
- pascal voc
- object classes
- feature vectors
- image processing
- image set
- image understanding
- key frames
- video data
- markov random field
- long range
- natural images
- information extraction
- viewpoint
- feature space
- face recognition
- image segmentation
- training data