Relieving Pixel-Wise Labeling Effort for Pathology Image Segmentation with Self-training.
Romain MormontMehdi TestouriRaphaël MaréePierre GeurtsPublished in: ECCV Workshops (7) (2022)
Keyphrases
- pixel wise
- image segmentation
- labeling effort
- active learning
- training set
- labeled data
- spatial information
- semi supervised learning
- multiscale
- computer vision
- foreground objects
- background subtraction
- active contours
- pixel level
- object segmentation
- markov random field
- image analysis
- template matching
- appearance model
- unlabeled data
- semi supervised
- segmentation method
- decision trees
- data sets
- level set
- machine learning
- segmentation algorithm
- deformable models
- expectation maximization
- supervised learning
- training data
- prior knowledge