Simpler is Better: Spectral Regularization and Up-Sampling Techniques for Variational Autoencoders.
Sara BjörkJonas Nordhaug MyhreThomas Haugland JohansenPublished in: ICASSP (2022)
Keyphrases
- denoising
- total variation regularization
- variational formulation
- variational framework
- basis pursuit
- sampling strategy
- image segmentation
- variational methods
- random sampling
- total variation
- sampling methods
- restricted boltzmann machine
- hyperspectral
- spectral analysis
- image denoising
- smoothness term
- monte carlo
- robust statistics
- active learning
- optical flow computation
- computer vision
- prior information
- optical flow
- regularization methods
- level set
- free energy
- sample size
- hyperspectral images
- multispectral images
- regularization term