Weakly Supervised Intracranial Hemorrhage Segmentation Using Hierarchical Combination of Attention Maps from a Swin Transformer.
Amirhossein RasoulianSoorena SalariYiming XiaoPublished in: MLCN@MICCAI (2022)
Keyphrases
- weakly supervised
- semantic segmentation
- fully supervised
- superpixels
- segmentation algorithm
- segmentation method
- topic models
- object class
- medical images
- object segmentation
- image segmentation
- semi supervised
- level set
- multiscale
- relation extraction
- shape prior
- ct images
- visual attention
- named entities
- multiple objects
- bounding box
- object detectors
- test images
- shape model
- natural images