2026-09-18T19:40:11Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/101050 2023-07-11 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Lazebnik, Svetlana Huang, Jing 2018-09-04T20:27:25Z 2018-09-04T20:27:25Z 2018-04-24 2018-05 In this thesis, we apply deep convolutional neural networks to ne-grained artwork classification on the large-scale painting collection, WikiArt. We propose a new architecture that aggregates features from different convolutional layers to exploit earlier layer features. The new architecture is evaluated on the challenging fine-grained artist and year classification. We also propose a regularization method that penalizes correlations of convolutional feature maps. With the decorrelation regularization, we further improve the classification accuracy of the proposed architecture. Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2018-08-31 without embargo terms The student, Jing Huang, accepted the attached license on 2018-04-23 at 23:41. The student, Jing Huang, submitted this Thesis for approval on 2018-04-24 at 11:16. This Thesis was approved for publication on 2018-04-24 at 11:46. DSpace SAF Submission Ingestion Package generated from Vireo submission #12438 on 2018-08-31 at 17:14:21 Made available in DSpace on 2018-09-04T20:27:25Z (GMT). No. of bitstreams: 3 HUANG-THESIS-2018.pdf: 5213675 bytes, checksum: b482c935e04126b9f40610c23e273c54 (MD5) jhuang81-thesis-source-files.zip: 4704530 bytes, checksum: 6df225ac965d03ef46e177bcaf496ff2 (MD5) LICENSE.txt: 4207 bytes, checksum: a7344344909e5d378b8d424301c978ee (MD5) Previous issue date: 2018-04-24 application/pdf http://hdl.handle.net/2142/101050 en Copyright 2018 Jing Huang Convolutional Neural Networks Fine-grained Classification Artworks Classification Fine-grained artworks classification text text Computer Science Computer Science University of Illinois at Urbana-Champaign Thesis M.S.