SASFormer: Transformers for Sparsely Annotated Semantic Segmentation.
Hui SuYue YeWei HuaLechao ChengMingli SongPublished in: ICME (2023)
Keyphrases
- semantic segmentation
- street scenes
- image set
- conditional random fields
- label transfer
- superpixels
- scene classification
- weakly supervised
- object categories
- image understanding
- manually annotated
- object recognition
- annotated images
- object classes
- object class
- feature extraction
- segmentation algorithm
- graphical models
- object detection
- semi supervised
- hidden markov models