Self-guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs.
Constantin SeiboldJens KleesiekHeinz-Peter SchlemmerRainer StiefelhagenPublished in: ACCV (5) (2020)
Keyphrases
- weakly supervised learning
- multiple instance learning
- weakly supervised
- supervised learning
- class labels
- semi supervised
- classification accuracy
- object class
- chest radiographs
- multi class
- feature extraction
- relation extraction
- object detection
- image classification
- text classification
- machine learning
- unsupervised learning
- semi supervised learning
- topic models
- image annotation
- superpixels
- decision trees
- learning algorithm
- support vector machine
- active learning
- feature space
- reinforcement learning
- feature selection