Abstract
dc:description.abstractIn this thesis, we investigate the use of dictionary learning for discriminative tasks on natural images. Our contributions can be summarized as follows: • We introduce discriminative deviation based learning to achieve principled handling of the reconstruction-discrimination tradeoff that is inherent to discriminative dictionary learning. • Since natural images obey a strong smoothness prior, we show how spatial smoothness constraints can be incorporated into the learning formulation by embedding dictionary learning into Conditional Random Field (CRF) learning. We demonstrate that such smoothness constraints can lead to state-of-the-art performance for pixel-classification tasks. • Finally, we lay down the foundations of super-latent learning. By treating sparse codes on a CRF as latent variables, dictionary learning can also be performed via the Latent (Structural) SVM formulation for jointly learning a classifier over the sparse codes. The dictionary is treated as a super-latent variable that generates the latent variables.
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Khan, Muhammad Nazar
- Contributors dc:contributor
-
- Tappen, Marshall
Subjects
dc:subject × 2Rights
- Language dc:language
- English
Identifiers
dc:identifier.*- Identifier
- CFE0004701