PFGM++: Unlocking the Potential of Physics-Inspired Generative Models.
Yilun XuZiming LiuYonglong TianShangyuan TongMax TegmarkTommi S. JaakkolaPublished in: CoRR (2023)
Keyphrases
- generative model
- probabilistic model
- discriminative learning
- mixture model
- discriminative models
- hierarchical hidden markov models
- em algorithm
- prior knowledge
- object categories
- topic models
- semi supervised
- maximum entropy principle
- discriminatively trained
- conditional random fields
- hidden variables
- graphical models
- image segmentation
- expectation maximization
- support vector
- hidden markov models
- boltzmann machine
- generative and discriminative models
- learning algorithm