Domain Adaptation and Generalization: A Low-Complexity Approach

Joshua Niemeijer, Jörg Peter Schäfer
Proceedings of The 6th Conference on Robot Learning, PMLR 205:1081-1091, 2023.

Abstract

Well-performing deep learning methods are essential in today’s perception of robotic systems such as autonomous driving vehicles. Ongoing research is due to the real-life demands for robust deep learning models against numerous domain changes and cheap training processes to avoid costly manual-labeling efforts. These requirements are addressed by unsupervised domain adaptation methods, in particular for synthetic to real-world domain changes. Recent top-performing approaches are hybrids consisting of multiple adaptation technologies and complex training processes. In contrast, this work proposes EasyAdap, a simple and easy-to-use unsupervised domain adaptation method achieving near state-of-the-art performance on the synthetic to real-world domain change. Our evaluation consists of a comparison to numerous top-performing methods, and it shows the competitiveness and further potential of domain adaptation and domain generalization capabilities of our method. We contribute and focus on an extensive discussion revealing possible reasons for domain generalization capabilities, which is necessary to satisfy real-life application’s demands.

Cite this Paper

BibTeX
@InProceedings{pmlr-v205-niemeijer23a, title = {Domain Adaptation and Generalization: A Low-Complexity Approach}, author = {Niemeijer, Joshua and Sch\"afer, J\"org Peter}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {1081--1091}, year = {2023}, editor = {Liu, Karen and Kulic, Dana and Ichnowski, Jeff}, volume = {205}, series = {Proceedings of Machine Learning Research}, month = {14--18 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v205/niemeijer23a/niemeijer23a.pdf}, url = {https://proceedings.mlr.press/v205/niemeijer23a.html}, abstract = {Well-performing deep learning methods are essential in today’s perception of robotic systems such as autonomous driving vehicles. Ongoing research is due to the real-life demands for robust deep learning models against numerous domain changes and cheap training processes to avoid costly manual-labeling efforts. These requirements are addressed by unsupervised domain adaptation methods, in particular for synthetic to real-world domain changes. Recent top-performing approaches are hybrids consisting of multiple adaptation technologies and complex training processes. In contrast, this work proposes EasyAdap, a simple and easy-to-use unsupervised domain adaptation method achieving near state-of-the-art performance on the synthetic to real-world domain change. Our evaluation consists of a comparison to numerous top-performing methods, and it shows the competitiveness and further potential of domain adaptation and domain generalization capabilities of our method. We contribute and focus on an extensive discussion revealing possible reasons for domain generalization capabilities, which is necessary to satisfy real-life application’s demands. } }
Endnote
%0 Conference Paper %T Domain Adaptation and Generalization: A Low-Complexity Approach %A Joshua Niemeijer %A Jörg Peter Schäfer %B Proceedings of The 6th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Karen Liu %E Dana Kulic %E Jeff Ichnowski %F pmlr-v205-niemeijer23a %I PMLR %P 1081--1091 %U https://proceedings.mlr.press/v205/niemeijer23a.html %V 205 %X Well-performing deep learning methods are essential in today’s perception of robotic systems such as autonomous driving vehicles. Ongoing research is due to the real-life demands for robust deep learning models against numerous domain changes and cheap training processes to avoid costly manual-labeling efforts. These requirements are addressed by unsupervised domain adaptation methods, in particular for synthetic to real-world domain changes. Recent top-performing approaches are hybrids consisting of multiple adaptation technologies and complex training processes. In contrast, this work proposes EasyAdap, a simple and easy-to-use unsupervised domain adaptation method achieving near state-of-the-art performance on the synthetic to real-world domain change. Our evaluation consists of a comparison to numerous top-performing methods, and it shows the competitiveness and further potential of domain adaptation and domain generalization capabilities of our method. We contribute and focus on an extensive discussion revealing possible reasons for domain generalization capabilities, which is necessary to satisfy real-life application’s demands.
APA
Niemeijer, J. & Schäfer, J.P.. (2023). Domain Adaptation and Generalization: A Low-Complexity Approach. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:1081-1091 Available from https://proceedings.mlr.press/v205/niemeijer23a.html.

Related Material