Files in this item



application/pdf3392199.pdf (2MB)Restricted to U of Illinois
(no description provided)PDF


Title:A New Framework for Semisupervised, Multitask Learning
Author(s):Loeff, Nicolas
Doctoral Committee Chair(s):Ahuja, Narendra
Department / Program:Electrical and Computer Engineering
Discipline:Electrical and Computer Engineering
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):Engineering, Electronics and Electrical
Abstract:To conclude, we interpret the internal representation of the model and use it to perform unsupervised scene discovery. Defining a meaningful vocabulary for scene discovery is a challenging problem that has important consequences for object recognition. We consider scenes to depict correlated objects and present visual similarity. We postulate that the internal representation space of our model should allow us to discover a large number of scenes in unsupervised data; we show scene discrimination results on par with supervised approaches even without explicitly labeling scenes, producing highly plausible scene clusters.
Issue Date:2009
Description:73 p.
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2009.
Other Identifier(s):(MiAaPQ)AAI3392199
Date Available in IDEALS:2015-09-25
Date Deposited:2009

This item appears in the following Collection(s)

Item Statistics