Consistency regularization for unsupervised domain adaptation in semantic segmentation

  • Unsupervised domain adaptation is a promising technique for computer vision tasks, especially when annotating large amounts of data is very costly and time-consuming, as in semantic segmentation. Here it is attractive to train neural networks on simulated data and fit them to real data on which the models are to be used. In this paper, we propose a consistency regularization method for domain adaptation in semantic segmentation that combines pseudo-labels and strong per- turbations. We analyse the impact of two simple perturbations, dropout and image mixing, and show how they contribute enormously to the final performance. Experiments and ablation studies demonstrate that our simple approach achieves strong results on relevant synthetic-to-real domain adaptation benchmarks.

Download full text files

Export metadata


Number of document requests

Additional Services

Share in Twitter Search Google Scholar
Author:Sebastian SchererGND, Stephan BrehmORCiDGND, Rainer LienhartGND
Frontdoor URL
Parent Title (English):Lecture Notes in Computer Science
Place of publication:Berlin
Year of first Publication:2022
Publishing Institution:Universität Augsburg
Release Date:2022/04/25
First Page:500
Last Page:511
ICIAP 2021 - 21st International Conference on Image Analysis and Processing, May 23-27, 2022, Lecce, Italy, Proceedings, part 1. Edited by Stan Sclaroff, Cosimo Distante, Marco Leo, Giovanni M. Farinella, Federico Tombari.
Institutes:Fakultät für Angewandte Informatik
Fakultät für Angewandte Informatik / Institut für Informatik
Fakultät für Angewandte Informatik / Institut für Informatik / Lehrstuhl für Maschinelles Lernen und Maschinelles Sehen
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):Deutsches Urheberrecht