SC-MIL: Supervised Contrastive Multiple Instance Learning for Imbalanced Classification in Pathology.
Dinkar JuyalSiddhant ShingiSyed Ashar JavedHarshith PadigelaChintan ShahAnand SampatArchit KhoslaJohn AbelAmaro Taylor-WeinerPublished in: CoRR (2023)
Keyphrases
- multiple instance learning
- supervised learning
- image categorization
- multiple instance
- instance selection
- multi class
- class labels
- object based image retrieval
- semi supervised
- image annotation
- randomized trees
- unsupervised learning
- machine learning
- semi supervised learning
- support vector machine
- text classification
- class imbalance
- classification accuracy
- feature extraction
- diverse density
- localized content based image retrieval
- training data
- learning tasks
- image classification
- training set
- feature space
- feature selection
- learning problems
- multi label
- support vector
- image segmentation