abstract: Computer Vision as a eld has gone through signicant changes in the last decade.
The eld has seen tremendous success in designing learning systems with hand-crafted
features and in using representation learning to extract better features. In this dissertation
some novel approaches to representation learning and task learning are studied.
Multiple-instance learning which is generalization of supervised learning, is one
example of task learning that is discussed. In particular, a novel non-parametric k-
NN-based multiple-instance learning is proposed, which is shown to outperform other
existing approaches. This solution is applied to a diabetic retinopathy pathology
detection problem eectively.
In cases of representation learning, generality of neural features are investigated
rst. This investigation leads to some critical understanding and results in feature
generality among datasets. The possibility of learning from a mentor network instead
of from labels is then investigated. Distillation of dark knowledge is used to eciently
mentor a small network from a pre-trained large mentor network. These studies help
in understanding representation learning with smaller and compressed networks. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2017
| Identifer | oai:union.ndltd.org:asu.edu/item:46233 |
| Date | January 2017 |
| Contributors | Venkatesan, Ragav (Author), Li, Baoxin (Advisor), Turaga, Pavan (Committee member), Yang, Yezhou (Committee member), Davulcu, Hasan (Committee member), Arizona State University (Publisher) |
| Source Sets | Arizona State University |
| Language | English |
| Detected Language | English |
| Type | Doctoral Dissertation |
| Format | 138 pages |
| Rights | http://rightsstatements.org/vocab/InC/1.0/, All Rights Reserved |
Page generated in 0.0031 seconds