Colour augmentation for improved semi-supervised semantic segmentation

Geoffrey French, Michal Mackiewicz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Downloads (Pure)

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.

Original languageEnglish
Title of host publicationProceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - (Volume 4)
Pages356-363
Number of pages8
Volume4
DOIs
Publication statusPublished - 6 Feb 2022

Publication series

NameProceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
ISSN (Print)2184-5921

Keywords

  • Data Augmentation
  • Deep Learning
  • Semantic Segmentation
  • Semi-supervised Learning

Cite this