{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/99388"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/99388","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Fine-grained painting classification","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.","abstract_html":"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.","abstract_has_math":false,"creators":["Kedia, Manav"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Lazebnik, Svetlana"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-03-13T15:49:04Z","date_published":"2018-03-13T15:49:04Z","updated_at":"2026-07-22T22:24:37Z","subjects":["Painting","Classification","Styles","Artist","Multi-task","Visual Geometry Group (VGG)"],"languages":["en"],"rights":["Copyright 2017 Manav Kedia"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/99388","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Lazebnik, Svetlana"]},{"key":"dc:creator","label":"Author","values":["Kedia, Manav"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-03-13T15:49:04Z","2017-12-07","2017-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Painting","Classification","Styles","Artist","Multi-task","Visual Geometry Group (VGG)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2017 Manav Kedia"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/99388"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["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.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2018-03-13 without embargo terms","The student, Manav Kedia, accepted the attached license on 2017-12-07 at 00:27.","The student, Manav Kedia, submitted this Thesis for approval on 2017-12-07 at 00:33.","This Thesis was approved for publication on 2017-12-07 at 13:16.","DSpace SAF Submission Ingestion Package generated from Vireo submission #11893 on 2018-03-13 at 10:11:22","Made available in DSpace on 2018-03-13T15:49:04Z (GMT). No. of bitstreams: 3 KEDIA-THESIS-2017.pdf: 3001077 bytes, checksum: 887e63bfc9722374f901525bea158875 (MD5) Thesis.doc: 10739712 bytes, checksum: ec87c202ea13279c27a16d83e42307e5 (MD5) LICENSE.txt: 4208 bytes, checksum: b3594b86131c781bda7ae4f1b60e9133 (MD5) Previous issue date: 2017-12-07"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Fine-grained painting classification"]}]}],"canonical_facts":{"dc:contributor":["Lazebnik, Svetlana"],"dc:creator":["Kedia, Manav"],"dc:date":["2018-03-13T15:49:04Z","2017-12-07","2017-12"],"dc:description":["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.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2018-03-13 without embargo terms","The student, Manav Kedia, accepted the attached license on 2017-12-07 at 00:27.","The student, Manav Kedia, submitted this Thesis for approval on 2017-12-07 at 00:33.","This Thesis was approved for publication on 2017-12-07 at 13:16.","DSpace SAF Submission Ingestion Package generated from Vireo submission #11893 on 2018-03-13 at 10:11:22","Made available in DSpace on 2018-03-13T15:49:04Z (GMT). No. of bitstreams: 3 KEDIA-THESIS-2017.pdf: 3001077 bytes, checksum: 887e63bfc9722374f901525bea158875 (MD5) Thesis.doc: 10739712 bytes, checksum: ec87c202ea13279c27a16d83e42307e5 (MD5) LICENSE.txt: 4208 bytes, checksum: b3594b86131c781bda7ae4f1b60e9133 (MD5) Previous issue date: 2017-12-07"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/99388"],"dc:language":["en"],"dc:rights":["Copyright 2017 Manav Kedia"],"dc:subject":["Painting","Classification","Styles","Artist","Multi-task","Visual Geometry Group (VGG)"],"dc:title":["Fine-grained painting classification"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:37Z"}