Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs.
Jaewoong ChoiChangyeon YoonJunho LeeJung Ho ParkGeonho HwangMyungjoo KangPublished in: CoRR (2021)
Keyphrases
- latent space
- low dimensional
- lower dimensional
- manifold structure
- manifold learning
- latent variables
- parameter space
- high dimensional
- dimensionality reduction
- feature space
- gaussian process latent variable models
- generative model
- gaussian processes
- gaussian process
- matrix factorization
- transfer learning
- high dimensional data
- dimension reduction
- probabilistic latent semantic analysis
- body pose
- gaussian mixture
- random projections
- principal component analysis
- euclidean space
- distance metric
- sparse representation
- nonlinear dimensionality reduction
- feature extraction
- active learning
- high dimensional spaces
- semi supervised
- higher dimensional
- covariance matrix
- original data