English

Colour augmentation for improved semi-supervised semantic segmentation

Computer Vision and Pattern Recognition 2021-10-12 v1 Machine Learning

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, a number of successful approaches have been recently proposed. Recent work explored the challenges involved in using consistency regularization for segmentation problems. 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.

Keywords

Cite

@article{arxiv.2110.04487,
  title  = {Colour augmentation for improved semi-supervised semantic segmentation},
  author = {Geoff French and Michal Mackiewicz},
  journal= {arXiv preprint arXiv:2110.04487},
  year   = {2021}
}

Comments

9 pages, 1 figure

R2 v1 2026-06-24T06:45:26.948Z