Diversity vs. Recognizability: Human-like generalization in one-shot generative models.
Victor BoutinLakshya SinghalXavier ThomasThomas SerrePublished in: NeurIPS (2022)
Keyphrases
- generative model
- probabilistic model
- representational power
- mixture model
- discriminative learning
- discriminative models
- object categories
- em algorithm
- semi supervised
- conditional random fields
- hierarchical hidden markov models
- maximum entropy principle
- hidden variables
- topic models
- machine learning
- prior knowledge
- maximum entropy
- support vector
- bayesian networks
- image processing