PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Berger, A.H.* ; Lux, L.* ; Shit, S.* ; Ezhov, I.* ; Kaissis, G. ; Menten, M.J.* ; Rueckert, D.* ; Paetzold, J.C.*

Cross-domain and cross-dimension learning for image-to-graph transformers.

In: (2025 IEEE Winter Conference on Applications of Computer Vision, WACV 2025, 28 February - 4 March 2025, Tucson). 10662 Los Vaqueros Circle, Po Box 3014, Los Alamitos, Ca 90720-1264 Usa: Ieee Computer Soc, 2025. 64-74 (Proceedings - 2025 IEEE Winter Conference on Applications of Computer Vision, WACV 2025)
Postprint Research data DOI
Direct image-to-graph transformation is a challenging task that involves solving object detection and relationship prediction in a single model. Due to this task's complexity, large training datasets are rare in many domains, making the training of deep-learning methods challenging. This data sparsity necessitates transfer learning strategies akin to the state-of-the-art in general computer vision. In this work, we introduce a set of methods enabling cross-domain and cross-dimension learning for image-to-graph trans-formers. We propose (1) a regularized edge sampling loss to effectively learn object relations in multiple domains with different numbers of edges, (2) a domain adaptation frame-work for image-to-graph transformers aligning image- and graph-level features from different domains, and (3) a projection function that allows using 2D data for training 3D transformers. We demonstrate our method's utility in cross-domain and cross-dimension experiments, where we utilize labeled data from 2D road networks for simultaneous learning in vastly different target domains. Our method consistently outperforms standard transfer learning and self-supervised pretraining on challenging benchmarks, such as retinal or whole-brain vessel graph extraction.11Code: github.com/AlexanderHBerger/cross-dim_i2g
Altmetric
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Conference contribution
Keywords Domain Adaptation ; Image-to-graph ; Transfer Learning
Language english
Publication Year 2025
HGF-reported in Year 2025
ISSN (print) / ISBN [9798331510831]
Conference Title 2025 IEEE Winter Conference on Applications of Computer Vision, WACV 2025
Conference Date 28 February - 4 March 2025
Conference Location Tucson
Quellenangaben Volume: , Issue: , Pages: 64-74 Article Number: , Supplement: ,
Publisher Ieee Computer Soc
Publishing Place 10662 Los Vaqueros Circle, Po Box 3014, Los Alamitos, Ca 90720-1264 Usa
Institute(s) Institute for Machine Learning in Biomed Imaging (IML)
POF-Topic(s) 30205 - Bioengineering and Digital Health
Research field(s) Enabling and Novel Technologies
PSP Element(s) G-507100-001
Grants Bavarian Collaborative Research Project PRIPREKI of the Free State of Bavaria Funding Programme "Artificial Intelligence - Data Science" - Konrad Zuse School of Excellence in Reliable AI (relAI)
Medical Informatics Initiative
German Ministry of Education and Research
Stiftung der Deutschen Wirtschaft - German Research Foundation
DOI 10.1109/WACV61041.2025.00017
WOS ID 001481328900007
Scopus ID 105003639721
Erfassungsdatum 2025-05-22
[➜Report correction]