Understanding the (un)interpretability of natural image distributions using generative models.
Ryen KrusingaSohil ShahMatthias ZwickerTom GoldsteinDavid W. JacobsPublished in: CoRR (2019)
Keyphrases
- generative model
- natural images
- visual patterns
- natural scenes
- discriminative learning
- mixture model
- multiscale
- probabilistic model
- discriminative models
- bayesian framework
- denoising
- image denoising
- prior knowledge
- image statistics
- higher order
- input image
- em algorithm
- conditional random fields
- object recognition
- generative and discriminative models
- posterior probability
- probability distribution
- topic models
- image patches
- semi supervised
- hidden variables
- hierarchical hidden markov models
- random variables
- object categories
- superpixels
- object parts
- image processing
- discriminative methods
- expectation maximization
- image segmentation