Deep convolutional neural networks for semantic segmentation achieve outstanding accuracy, however they also have a couple of major drawbacks: first, they do not generalize well to distributions slightly different from the one of the training data; second, they require a huge amount of labeled data for their optimization. In this paper, we introduce feature-level space-shaping regularization strategies to reduce the domain discrepancy in semantic segmentation. In particular, for this purpose we jointly enforce a clustering objective, a perpendicularity constraint and a norm alignment goal on the feature vectors corresponding to source and target samples. Additionally, we propose a novel measure able to capture the relative efficacy of an adaptation strategy compared to supervised training. We verify the effectiveness of such methods in the autonomous driving setting achieving state-of-the-art results in multiple synthetic-to-real road scenes benchmarks.
@article{arxiv.2104.02633,
title = {Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation},
author = {Francesco Barbato and Marco Toldo and Umberto Michieli and Pietro Zanuttigh},
journal= {arXiv preprint arXiv:2104.02633},
year = {2021}
}
Comments
Accepted at CVPR-WAD 2021, 11 pages, 7 figures, 1 tables