Colour Augmentation for Improved Semi-supervised Semantic Segmentation

Geoff French, Michal Mackiewicz

2022

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

Download


Paper Citation


in Harvard Style

French G. and Mackiewicz M. (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 (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 356-363. DOI: 10.5220/0010807400003124


in Bibtex Style

@conference{visapp22,
author={Geoff French and Michal Mackiewicz},
title={Colour Augmentation for Improved Semi-supervised Semantic Segmentation},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={356-363},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010807400003124},
isbn={978-989-758-555-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Colour Augmentation for Improved Semi-supervised Semantic Segmentation
SN - 978-989-758-555-5
AU - French G.
AU - Mackiewicz M.
PY - 2022
SP - 356
EP - 363
DO - 10.5220/0010807400003124
PB - SciTePress