Variational Autoencoder for Deep Learning of Images, Labels and Captions.
Yunchen PuZhe GanRicardo HenaoXin YuanChunyuan LiAndrew StevensLawrence CarinPublished in: CoRR (2016)
Keyphrases
- deep learning
- image database
- input image
- restricted boltzmann machine
- image classification
- region of interest
- test images
- object recognition
- image retrieval
- unsupervised learning
- image features
- lighting conditions
- image segmentation
- model selection
- multiple images
- higher order
- co occurrence
- graphical models
- segmentation algorithm
- image regions
- training data