Colour augmentation for improved semi-supervised semantic segmentation

French, Geoffrey and Mackiewicz, Michal ORCID: https://orcid.org/0000-0002-8777-8880 (2022) Colour augmentation for improved semi-supervised semantic segmentation. In: Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - (Volume 4). Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 4 . UNSPECIFIED, pp. 356-363.

[thumbnail of col_aug_sem_seg_v3__visigrapp]
Preview
PDF (col_aug_sem_seg_v3__visigrapp) - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (307kB) | Preview

Abstract

Consistency regularization describes a class of approaches that have yielded state-of-the-art results for semi-supervised classification. While semi-supervised semantic segmentation proved to be more challenging, recent work has explored the challenges involved in using consistency regularization for segmentation problems and has presented solutions. In their self-supervised work Chen et al. found that colour augmentation prevents a classification network from using image colour statistics as a short-cut for self-supervised learning via instance discrimination. Drawing inspiration from this we find that a similar problem impedes semi-supervised semantic segmentation and offer colour augmentation as a solution, improving semi-supervised semantic segmentation performance on challenging photographic imagery. Implementation at: https://github.com/Britefury/cutmix-semisup-seg.

Item Type: Book Section
Additional Information: Funding Information: This work was funded under the European Union Horizon 2020 SMARTFISH project, grant agreement no. 773521. The computation required by this work was performed on the University of East Anglia HPC Cluster. Publisher Copyright: © 2021 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.
Uncontrolled Keywords: data augmentation,deep learning,semantic segmentation,semi-supervised learning,computer graphics and computer-aided design,computer vision and pattern recognition,human-computer interaction ,/dk/atira/pure/subjectarea/asjc/1700/1704
Faculty \ School: Faculty of Science > School of Computing Sciences
UEA Research Groups: Faculty of Science > Research Groups > Colour and Imaging Lab
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 24 May 2022 12:12
Last Modified: 19 Jun 2024 23:49
URI: https://ueaeprints.uea.ac.uk/id/eprint/85050
DOI: 10.5220/0010807400003124

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item