MIL-VT: Multiple Instance Learning Enhanced Vision Transformer for Fundus Image Classification.
Shuang YuKai MaQi BiCheng BianMunan NingNanjun HeYuexiang LiHanruo LiuYefeng ZhengPublished in: MICCAI (8) (2021)
Keyphrases
- multiple instance learning
- image classification
- multiple instance
- image categorization
- image annotation
- visual features
- multi class
- object based image retrieval
- supervised learning
- computer vision
- image features
- image representation
- multi label
- feature extraction
- image processing
- image search
- diverse density
- localized content based image retrieval
- semi supervised
- semi supervised learning
- classification accuracy
- multiscale
- data sets