Fine-grained artworks classification

Convolutional Neural Networks;Fine-grained Classification;Artworks Classification

Huang, Jing ; Lazebnik ; Svetlana

关键词: Convolutional Neural Networks;    Fine-grained Classification;    Artworks Classification;   

Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/101050/HUANG-THESIS-2018.pdf?sequence=1&isAllowed=y

美国|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

In this thesis, we apply deep convolutional neural networks tone-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 challengingfine-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.