Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels.
Yuchao WangHaochen WangYujun ShenJingjing FeiWei LiGuoqiang JinLiwei WuRui ZhaoXinyi LePublished in: CVPR (2022)
Keyphrases
- semantic segmentation
- semi supervised
- weakly supervised
- supervised methods
- conditional random fields
- superpixels
- scene classification
- semi supervised learning
- pairwise
- labeled data
- label transfer
- supervised learning
- multi view
- unlabeled data
- active learning
- object categories
- object classes
- generative model
- object class
- object recognition
- image set
- object segmentation
- machine learning
- decision trees
- similarity measure
- bayesian networks
- pascal voc
- multiscale
- bounding box
- hidden markov models
- image features
- higher order