A Closer Look at Self-Training for Zero-Label Semantic Segmentation.
Giuseppe PastoreFabio CermelliYongqin XianMassimiliano ManciniZeynep AkataBarbara CaputoPublished in: CVPR Workshops (2021)
Keyphrases
- semantic segmentation
- street scenes
- superpixels
- conditional random fields
- label transfer
- weakly supervised
- pascal voc
- scene classification
- training set
- multi label
- object categories
- object class
- bag of words
- object classes
- image understanding
- image set
- machine learning
- semi supervised learning
- object recognition
- segmentation algorithm
- higher order
- object segmentation
- multiscale
- object detection
- graph structure
- input image
- semi supervised
- probabilistic model
- text classification
- image representation
- computer vision