elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Domain Adaptation and Generalization: A Low-Complexity Approach

Niemeijer, Joshua and Schäfer, Jörg P. (2022) Domain Adaptation and Generalization: A Low-Complexity Approach. Conference on Robot Learning (CoRL) 2022, 2022-12-14 - 2022-12-18, Auckland, New Zealand. ISSN 26403498.

[img] PDF - Only accessible within DLR
24MB

Official 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.

Item URL in elib:https://elib.dlr.de/192935/
Document Type:Conference or Workshop Item (Speech)
Title:Domain Adaptation and Generalization: A Low-Complexity Approach
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Niemeijer, JoshuaUNSPECIFIEDhttps://orcid.org/0000-0002-2417-8749UNSPECIFIED
Schäfer, Jörg P.UNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Date:December 2022
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
ISSN:26403498
Status:Published
Keywords:unsupervised domain adaptation, semantic segmentation, domain generalization
Event Title:Conference on Robot Learning (CoRL) 2022
Event Location:Auckland, New Zealand
Event Type:international Conference
Event Start Date:14 December 2022
Event End Date:18 December 2022
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Road Transport
DLR - Research area:Transport
DLR - Program:V ST Straßenverkehr
DLR - Research theme (Project):V - KoKoVI - Koordinierter kooperativer Verkehr mit verteilter, lernender Intelligenz
Location: Berlin-Adlershof , Braunschweig
Institutes and Institutions:Institute of Transportation Systems
Institute of Transportation Systems > Cooperative Systems, BS
Institute of Transportation Systems > Cooperative Systems, BA
Deposited By: Niemeijer, Joshua
Deposited On:10 Jan 2023 10:02
Last Modified:27 May 2024 13:30

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.