Robust Semantic Segmentation with Superpixel-Mix

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 metho...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Franchi, Gianni, Belkhir, Nacim, Mai Lan Ha, Hu, Yufei, Bursuc, Andrei, Blanz, Volker, Yao, Angela
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 21.10.2021
Subjects
Bias
Data augmentation
Image segmentation
Network reliability
Performance prediction
Semantic segmentation
Semantics
Uncertainty
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422