ADMM penalty parameter selection with krylov subspace recycling technique for sparse coding.
Youzuo LinBrendt WohlbergVelimir VesselinovPublished in: ICIP (2017)
Keyphrases
- parameter selection
- sparse coding
- feature space
- dictionary learning
- sparse representation
- high dimensional
- natural images
- linear combination
- image classification
- low dimensional
- image representation
- unsupervised learning
- dimensionality reduction
- principal component analysis
- high dimensional data
- image patches
- model selection
- generative model
- visual words
- total variation
- convex optimization
- feature extraction
- dimension reduction
- object recognition
- data mining
- input data
- nearest neighbor
- image features
- feature vectors
- machine learning