A New Framework for Semisupervised, Multitask Learning

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.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Electrical and Computer Engineering

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2015

Author dc:creator

• Loeff, Nicolas

Contributors dc:contributor

• Ahuja, Narendra

• Engineering, Electronics and Electrical

Language dc:language

eng

Identifier

(MiAaPQ)AAI3392199

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/81142