Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-12 · 45 (12) · 14234-14247
DOI: 10.1109/tpami.2023.3310261 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-12. Verfasst von Cristiano Saltori und 5 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: OSRAM GmbH, MUR PNRR, FAIR.
Abstract (Originalsprache)
Deep-learning models for 3D point cloud semantic segmentation exhibit limited generalization capabilities when trained and tested on data captured with different sensors or in varying environments due to domain shift. Domain adaptation methods can be employed to mitigate this domain shift, for instance, by simulating sensor noise, developing domain-agnostic generators, or training point cloud completion networks. Often, these methods are tailored for range view maps or necessitate multi-modal input. In contrast, domain adaptation in the image domain can be executed through sample mixing, which emphasizes input data manipulation rather than employing distinct adaptation modules. In this study, we introduce compositional semantic mixing for point cloud domain adaptation, representing the first unsupervised domain adaptation technique for point cloud segmentation based on semantic and geometric sample mixing. We present a two-branch symmetric network architecture capable of concurrently processing point clouds from a source domain (e.g. synthetic) and point clouds from a target domain (e.g. real-world). Each branch operates within one domain by integrating selected data fragments from the other domain and utilizing semantic information derived from source labels and target (pseudo) labels. Additionally, our method can leverage a limited number of human point-level annotations (semi-supervised) to further enhance performance. We assess our approach in both synthetic-to-real and real-to-real scenarios using LiDAR datasets and demonstrate that it significantly outperforms state-of-the-art methods in both unsupervised and semi-supervised settings.
Förderung
- OSRAM GmbH
- MUR PNRR
- FAIR
- NextGenerationEU
- EU project FEROX
- PRIN PREVUE
- EU ISFP PRECRISIS
- EU H2020 MARVEL
Zitieren
APA
Saltori, C., Galasso, F., Fiameni, G., Sebe, N., Poiesi, F., & Ricci, E. (2023). Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(12), 14234-14247. https://doi.org/10.1109/tpami.2023.3310261
Vancouver
Saltori C, Galasso F, Fiameni G, Sebe N, Poiesi F, Ricci E. Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(12):14234-14247. doi:10.1109/tpami.2023.3310261
BibTeX
@article{Saltori2023,
author = {Saltori, Cristiano and Galasso, Fabio and Fiameni, Giuseppe and Sebe, Nicu and Poiesi, Fabio and Ricci, Elisa},
title = {Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2023},
volume = {45},
number = {12},
pages = {14234--14247},
doi = {10.1109/tpami.2023.3310261}
}
EUVIMED