A Closer Look at Self-training for Zero-Label Semantic Segmentation.
Giuseppe PastoreFabio CermelliYongqin XianMassimiliano ManciniZeynep AkataBarbara CaputoPublished in: CoRR (2021)
Keyphrases
- prior knowledge
- semantic segmentation
- street scenes
- label transfer
- superpixels
- conditional random fields
- weakly supervised
- scene classification
- image understanding
- pascal voc
- semi supervised
- machine learning
- object categories
- object classes
- object class
- higher order
- semi supervised learning
- multi label
- training set
- bag of words
- graph cuts
- text classification
- viewpoint
- object recognition
- decision trees