How to scale hyperparameters for quickshift image segmentation.
Damien GarreauPublished in: AISTATS (2022)
Keyphrases
- hyperparameters
- image segmentation
- cross validation
- model selection
- random sampling
- closed form
- bayesian inference
- bayesian framework
- maximum a posteriori
- em algorithm
- sample size
- support vector
- prior information
- gaussian process
- markov random field
- noise level
- regularization parameter
- incremental learning
- gaussian processes
- maximum likelihood
- expectation maximization
- incomplete data
- parameter settings
- level set
- image processing
- missing values
- graph cuts
- multiscale
- parameter space
- active learning
- pairwise
- lower bound
- decision trees