Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation.
Jiaqi GuHyoukjun KwonDilin WangWei YeMeng LiYu-Hsin ChenLiangzhen LaiVikas ChandraDavid Z. PanPublished in: CVPR (2022)
Keyphrases
- semantic segmentation
- multiscale
- superpixels
- high resolution
- image processing
- street scenes
- low resolution
- conditional random fields
- weakly supervised
- label transfer
- natural images
- super resolution
- computer vision
- scene classification
- vision system
- scale space
- object class
- object categories
- remote sensing
- image segmentation
- high quality
- image understanding
- pixel level
- image representation
- pascal voc
- keypoints
- object classes
- object recognition
- generative model
- text classification
- markov random field
- feature extraction
- face images
- denoising