Files in this item

FilesDescriptionFormat

application/pdf

application/pdfKEDIA-THESIS-2017.pdf (3MB)
(no description provided)PDF

Description

Title:Fine-grained painting classification
Author(s):Kedia, Manav
Advisor(s):Lazebnik, Svetlana
Department / Program:Computer Science
Discipline:Computer Science
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:M.S.
Genre:Thesis
Subject(s):Painting
Classification
Styles
Artist
Multi-task
Visual Geometry Group (VGG)
Abstract:A lot of progress has been made in the domain of image classification in the deep learning era, however, not so much for paintings. Even though paintings are images they are very different from photographs and classification of paintings requires in-depth domain knowledge compared to classifying an object. This makes the task of fine-grained classification of paintings even harder. In this thesis, we evaluate the classification of paintings into its various styles, genres, artists and formulate the problem of dating paintings as a classification problem. We experiment with the standard networks available as baselines and then improve the classification models via multi-task learning. We also propose a novel architectural addition to the VGG network to do fine-grained classification. Our models beat the existing state-of-the-art classifiers by a big margin.
Issue Date:2017-12-07
Type:Text
URI:http://hdl.handle.net/2142/99388
Rights Information:Copyright 2017 Manav Kedia
Date Available in IDEALS:2018-03-13
Date Deposited:2017-12


This item appears in the following Collection(s)

Item Statistics