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.
@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}
}