Exploring Vision Transformer Layer Choosing for Semantic Segmentation.
Fangjian LinYizhe MaShengWei TianPublished in: ICASSP (2023)
Keyphrases
- semantic segmentation
- street scenes
- conditional random fields
- label transfer
- superpixels
- weakly supervised
- scene classification
- pascal voc
- computer vision
- vision system
- object categories
- object detection
- image set
- object class
- object classes
- natural images
- image processing
- image understanding
- natural scenes
- co occurrence
- multiscale
- machine learning