Mridula Vijendran mridula.vijendran@durham.ac.uk
PGR Student Doctor of Philosophy
Tackling Data Bias in Painting Classification with Style Transfer
Vijendran, Mridula; Li, Frederick W.B.; Shum, Hubert P.H.
Authors
Dr Frederick Li frederick.li@durham.ac.uk
Associate Professor
Professor Hubert Shum hubert.shum@durham.ac.uk
Professor
Abstract
It is difficult to train classifiers on paintings collections due to model bias from domain gaps and data bias from the uneven distribution of artistic styles. Previous techniques like data distillation, traditional data augmentation and style transfer improve classifier training using task specific training datasets or domain adaptation. We propose a system to handle data bias in small paintings datasets like the Kaokore dataset while simultaneously accounting for domain adaptation in fine-tuning a model trained on real world images. Our system consists of two stages which are style transfer and classification. In the style transfer stage, we generate the stylized training samples per class with uniformly sampled content and style images and train the style transformation network per domain. In the classification stage, we can interpret the effectiveness of the style and content layers at the attention layers when training on the original training dataset and the stylized images. We can tradeoff the model performance and convergence by dynamically varying the proportion of augmented samples in the majority and minority classes. We achieve comparable results to the SOTA with fewer training epochs and a classifier with fewer training parameters.
Citation
Vijendran, M., Li, F. W., & Shum, H. P. (2023, February). Tackling Data Bias in Painting Classification with Style Transfer. Presented at VISAPP '23: 2023 International Conference on Computer Vision Theory and Applications, Lisbon, Portugal
Presentation Conference Type | Conference Paper (published) |
---|---|
Conference Name | VISAPP '23: 2023 International Conference on Computer Vision Theory and Applications |
Start Date | Feb 19, 2023 |
End Date | Feb 21, 2023 |
Acceptance Date | Dec 22, 2022 |
Publication Date | 2023 |
Deposit Date | Jan 6, 2023 |
Publicly Available Date | Jan 6, 2023 |
Volume | 5 |
Pages | 250-261 |
Series ISSN | 2184-4321 |
Book Title | Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP |
ISBN | 9789897586347 |
DOI | https://doi.org/10.5220/0011776600003417 |
Public URL | https://durham-repository.worktribe.com/output/1134273 |
Files
Accepted Conference Proceeding
(2.8 Mb)
PDF
Licence
http://creativecommons.org/licenses/by-nc-nd/4.0/
Publisher Licence URL
http://creativecommons.org/licenses/by-nc-nd/4.0/
You might also like
A Differential Diffusion Theory for Participating Media
(2023)
Journal Article
An end-to-end dynamic point cloud geometry compression in latent space
(2023)
Journal Article
IAACS: Image Aesthetic Assessment Through Color Composition And Space Formation
(2023)
Journal Article
Downloadable Citations
About Durham Research Online (DRO)
Administrator e-mail: dro.admin@durham.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2025
Advanced Search