T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00371716" target="_blank" >RIV/68407700:21230/23:00371716 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/IROS55552.2023.10341446" target="_blank" >https://doi.org/10.1109/IROS55552.2023.10341446</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/IROS55552.2023.10341446" target="_blank" >10.1109/IROS55552.2023.10341446</a>
Alternative languages
Result language
angličtina
Original language name
T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds
Original language description
Deep perception models have to reliably cope with an open-world setting of domain shifts induced by different geographic regions, sensor properties, mounting positions, and several other reasons. Since covering all domains with annotated data is technically intractable due to the endless possible variations, researchers focus on unsupervised domain adaptation (UDA) methods that adapt models trained on one (source) domain with annotations available to another (target) domain for which only unannotated data are available. Current predominant methods either leverage semi-supervised approaches, e.g., teacher-student setup, or exploit privileged data, such as other sensor modalities or temporal data consistency. We introduce a novel domain adaptation method that leverages the best of both approaches. Our approach combines input data's temporal and cross-sensor geometric consistency with the mean teacher method. Dubbed T-UDA for “temporal UDA”, such a combination yields massive performance gains for the task of 3D semantic segmentation of driving scenes. Experiments are conducted on Waymo Open Dataset, nuScenes, and SemanticKITTI, for two popular 3D point cloud architectures, Cylinder3D and MinkowskiNet. Our codes are publicly available on https://github.com/ctu-vras/T-UDA.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
ISBN
978-1-6654-9190-7
ISSN
2153-0858
e-ISSN
2153-0866
Number of pages
8
Pages from-to
7643-7650
Publisher name
IEEE
Place of publication
Piscataway
Event location
Detroit, MA
Event date
Oct 1, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001136907802008