Colour Augmentation for Improved Semi-supervised Semantic Segmentation

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: hfips://github.com/Britefury/cutmix-semisup-seg.