% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Schacht:639444,
author = {Schacht, Benedict and Greving, Imke and Frintrop, Simone
and Zeller-Plumhoff, Berit and Wilms, Christian},
title = {{C}ontextloss: {C}ontext {I}nformation for
{T}opology-{P}reserving {S}egmentation},
address = {[Piscataway, NJ]},
publisher = {IEEE},
reportid = {PUBDB-2025-04532},
isbn = {979-8-3315-2379-4},
pages = {1882 - 1887},
year = {2025},
note = {"This year's ICIP theme is 'Image processing in the age of
GenAI'" - Vorwort; Literaturangaben;},
comment = {[Ebook] 2025 IEEE International Conference on Image
Processing (ICIP) : proceedings : 14-17 September 2025,
Anchorage, Alaska, United States / sponsored by: the
Institute of Electrical and Electronics Engineers, Signal
Processing Society , [Piscataway, NJ] : IEEE, 2025,},
booktitle = {[Ebook] 2025 IEEE International
Conference on Image Processing (ICIP) :
proceedings : 14-17 September 2025,
Anchorage, Alaska, United States /
sponsored by: the Institute of
Electrical and Electronics Engineers,
Signal Processing Society ,
[Piscataway, NJ] : IEEE, 2025,},
abstract = {In image segmentation, preserving the topology of segmented
structures like vessels, membranes, or roads is crucial. For
instance, topological errors on road networks can
significantly impact navigation. Recently proposed solutions
are loss functions based on critical pixel masks that
consider the whole skeleton of the segmented structures in
the critical pixel mask. We propose the novel loss function
ContextLoss (CLoss) that improves topological correctness by
considering topological errors with their whole context in
the critical pixel mask. The additional context improves the
network focus on the topological errors. Further, we propose
two intuitive metrics to verify improved connectivity due to
a closing of missed connections. We benchmark our proposed
CLoss on three public datasets (2D $\&$ 3D) and our own 3D
nano-imaging dataset of bone cement lines. Training with our
proposed CLoss increases performance on topology-aware
metrics and repairs up to 44 $\%$ more missed connections
than other state-of-the-art methods. We make the code
publicly available1 2.},
month = {Sep},
date = {2025-09-14},
organization = {2025 IEEE International Conference on
Image Processing, Anchorage (AK), 14
Sep 2025 - 17 Sep 2025},
cin = {Hereon / DOOR ; HAS-User},
cid = {I:(DE-H253)Hereon-20210428 / I:(DE-H253)HAS-User-20120731},
pnm = {6G3 - PETRA III (DESY) (POF4-6G3) / HIDSS-0002 - DASHH:
Data Science in Hamburg - Helmholtz Graduate School for the
Structure of Matter $(2019_IVF-HIDSS-0002)$},
pid = {G:(DE-HGF)POF4-6G3 / $G:(DE-HGF)2019_IVF-HIDSS-0002$},
experiment = {EXP:(DE-H253)P-P05-20150101},
typ = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
doi = {10.1109/ICIP55913.2025.11084563},
url = {https://bib-pubdb1.desy.de/record/639444},
}