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: WACV (2024)
Keyphrases
- multiple instance learning
- supervised learning
- image categorization
- multiple instance
- instance selection
- multi class
- class labels
- semi supervised
- object based image retrieval
- diverse density
- image annotation
- semi supervised learning
- support vector machine
- unsupervised learning
- labeled data
- class imbalance
- localized content based image retrieval
- randomized trees
- machine learning
- classification accuracy
- unlabeled data
- feature selection
- regression problems
- image classification
- learning problems
- text classification
- training examples
- training samples
- object recognition
- support vector
- training data
- real valued
- machine learning algorithms
- training set
- multiscale
- similarity measure
- positive bags
- feature extraction
- multi modal