Enhancing Reinforcement Learning Finetuned Text-to-Image Generative Model Using Reward Ensemble.
Kyungryul BackXinYu PiaoJong-Kook KimPublished in: ITS (2) (2024)
Keyphrases
- generative model
- reinforcement learning
- bayesian framework
- image content
- image classification
- input image
- image features
- image retrieval
- probabilistic model
- posterior probability
- visual patterns
- image segmentation
- multiscale
- image representation
- high resolution
- semi supervised
- prior knowledge
- topic models
- primal sketch
- machine learning
- low level
- learning algorithm
- text mining
- probability distribution
- data sets
- discriminative models
- information retrieval
- similarity measure
- reward function
- feature selection
- object categories
- hierarchical bayesian model
- latent dirichlet allocation
- image structure
- image set
- test images
- training data
- object recognition
- feature space
- em algorithm