CRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer.
Le Thi Thu HongNguyen Chi ThanhTran Quoc LongPublished in: IEEE Access (2021)
Keyphrases
- loss function
- conditional random fields
- pairwise
- segmentation method
- segmentation algorithm
- risk minimization
- random fields
- test images
- superpixels
- input image
- graphical models
- boosting framework
- image regions
- probabilistic model
- image classification
- image retrieval
- crf model
- semantic segmentation
- markov random field
- image features
- learning algorithm
- information extraction
- maximum entropy
- image segmentation
- region growing
- medical image retrieval
- boosting algorithms
- support vector
- medical images
- level set