Representation Separation for Semantic Segmentation with Vision Transformers.
Yuanduo HongHuihui PanWeichao SunXinghu YuHuijun GaoPublished in: CoRR (2022)
Keyphrases
- semantic segmentation
- street scenes
- computer vision
- conditional random fields
- superpixels
- label transfer
- weakly supervised
- scene classification
- image understanding
- object categories
- object class
- image representation
- image processing
- object classes
- image set
- spatial information
- pascal voc
- vision system
- object detection
- hidden markov models