Colour augmentation for improved semi-supervised semantic segmentation
This addresses a specific bottleneck in semi-supervised segmentation for computer vision applications, but is incremental as it adapts an existing idea from self-supervised learning.
The paper tackled the challenge of semi-supervised semantic segmentation by identifying that color statistics act as a shortcut, and proposed color augmentation as a solution, improving performance on photographic imagery.
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.