Semantic Instance Segmentation with a Discriminative Loss Function.
Bert De BrabandereDavy NevenLuc Van GoolPublished in: CoRR (2017)
Keyphrases
- loss function
- pairwise
- support vector
- logistic regression
- image segmentation
- level set
- reproducing kernel hilbert space
- boosting framework
- segmentation algorithm
- learning to rank
- hinge loss
- risk minimization
- energy function
- feature extraction
- feature selection
- convex loss functions
- empirical risk
- solution path
- stochastic gradient descent
- boosting algorithms
- regularization term
- kernel methods
- markov random field
- semi supervised