Attribute-based regularization of latent spaces for variational auto-encoders.
Ashis PatiAlexander LerchPublished in: Neural Comput. Appl. (2021)
Keyphrases
- variational formulation
- variational framework
- latent space
- image segmentation
- regularization methods
- latent variables
- smoothness term
- robust statistics
- inverse scale space
- methods in computer vision
- total variation regularization
- parameter selection
- video compression
- energy functional
- variational methods
- regularization parameter
- optical flow
- free energy
- inverse problems
- basis pursuit
- image processing
- bayesian networks
- regularization framework
- prior information
- level set
- shape prior