Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation.
Yi LiYiqun DuanZhanghui KuangYimin ChenWayne ZhangXiaomeng LiPublished in: CoRR (2021)
Keyphrases
- weakly supervised
- semantic segmentation
- superpixels
- object class
- topic models
- conditional random fields
- relation extraction
- segmentation algorithm
- semi supervised
- bounding box
- long range
- named entities
- object classes
- object categories
- information extraction
- multiscale
- bayesian networks
- visual features
- object segmentation
- natural images
- co occurrence
- input image
- automatic extraction
- hidden markov models
- pascal voc
- viewpoint