Unsupervised Domain Adaptation via Representation Learning

Please enable javascript in your browser.

Gheisary, Marzieh | 2015

605 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 46865 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Soleymani, Mahdieh
Abstract:
The existing learning methods usually assume that training and test data follow the same distribution, while this is not always true. Thus, in many cases the performance of these learning methods on the test data will be severely degraded. We often have sufficient labeled training data from a source domain but wish to learn a classifier which performs well on a target domain with a different distribution and no labeled training data. In this thesis, we study the problem of unsupervised domain adaptation, where no labeled data in the target domain is available. We propose a framework which finds a new representation for both the source and the target domain in which the distance between these domains has been reduced and also learns a prediction function in this new space. Moreover, we explore the problem of learning jointly the new representation and the classifier. We run the proposed method on standard benchmark datasets for visual object classification and show that the proposed method significantly outperforms state-of-the-art domain adaptation methods
Keywords:
Object Detection ; Unsupervised Learning ; Semi-Supervised Learning ; Domain Adaptation ; Representation Learning ; Source Domain ; Target Domain

No TOC