Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation. Reliability encompasses robustness, predictive uncertainty and reduced bias. To improve reliability, we introduce Superpixel-mix, a new superpixel-based data augmentation method with teacher-student consistency training. Unlike other mixing-based augmentation techniques, mixing superpixels between images is aware of object boundaries, while yielding consistent gains in segmentation accuracy. Our proposed technique achieves state-of-the-art results in semi-supervised semantic segmentation on the Cityscapes dataset. Moreover, Superpixel-mix improves the reliability of semantic segmentation by reducing network uncertainty and bias, as confirmed by competitive results under strong distributions shift (adverse weather, image corruptions) and when facing out-of-distribution data.
@article{arxiv.2108.00968,
title = {Robust Semantic Segmentation with Superpixel-Mix},
author = {Gianni Franchi and Nacim Belkhir and Mai Lan Ha and Yufei Hu and Andrei Bursuc and Volker Blanz and Angela Yao},
journal= {arXiv preprint arXiv:2108.00968},
year = {2021}
}