IOSUDA: an unsupervised domain adaptation with input and output space alignment for joint optic disc and cup segmentation.
Chonglin ChenGang WangPublished in: Appl. Intell. (2021)
Keyphrases
- optic disc
- fundus images
- output space
- input space
- retinal images
- structured output
- circular hough transform
- blood vessels
- ellipse fitting
- representative set
- retinal fundus images
- optical coherence tomography
- high dimensional
- diabetic retinopathy
- user defined
- class labels
- training set
- multiscale
- input data
- dimensionality reduction
- supervised learning