Test-Time Training for Semantic Segmentation with Output Contrastive Loss.
Yunlong ZhangYuxuan SunSunyi ZhengZhongyi ShuiChenglu ZhuLin YangPublished in: CoRR (2023)
Keyphrases
- semantic segmentation
- street scenes
- label transfer
- superpixels
- conditional random fields
- image understanding
- training set
- weakly supervised
- scene classification
- supervised learning
- training examples
- object classes
- pascal voc
- object categories
- biologically inspired
- face recognition
- image set
- bag of words
- d objects
- multiscale