kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Task adapted reconstruction for inverse problems
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematics (Div.). DeepMind, 6 Pancras Square, London, N1C 4AG, United Kingdom.ORCID iD: 0000-0001-9928-3407
Univ Cambridge, Ctr Math Sci, Cambridge CB3 0WA, England..
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematics (Div.). Department of Computing, Mathematics and Physics, Western Norway University of Applied Sciences, Bergen, Norway.ORCID iD: 0000-0003-3699-6244
Univ Cambridge, Ctr Math Sci, Cambridge CB3 0WA, England..
Show others and affiliations
2022 (English)In: Inverse Problems, ISSN 0266-5611, E-ISSN 1361-6420, Vol. 38, no 7, article id 075006Article in journal (Refereed) Published
Abstract [en]

The paper considers the problem of performing a post-processing task defined on a model parameter that is only observed indirectly through noisy data in an ill-posed inverse problem. A key aspect is to formalize the steps of reconstruction and post-processing as appropriate estimators (non-randomized decision rules) in statistical estimation problems. The implementation makes use of (deep) neural networks to provide a differentiable parametrization of the family of estimators for both steps. These networks are combined and jointly trained against suitable supervised training data in order to minimize a joint differentiable loss function, resulting in an end-to-end task adapted reconstruction method. The suggested framework is generic, yet adaptable, with a plug-and-play structure for adjusting both the inverse problem and the post-processing task at hand. More precisely, the data model (forward operator and statistical model of the noise) associated with the inverse problem is exchangeable, e.g., by using neural network architecture given by a learned iterative method. Furthermore, any post-processing that can be encoded as a trainable neural network can be used. The approach is demonstrated on joint tomographic image reconstruction, classification and joint tomographic image reconstruction segmentation.

Place, publisher, year, edition, pages
IOP Publishing , 2022. Vol. 38, no 7, article id 075006
Keywords [en]
inverse problems, image reconstruction, tomography, deep learning, feature reconstruction, segmentation, classification
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-314231DOI: 10.1088/1361-6420/ac28ecISI: 000803700500001Scopus ID: 2-s2.0-85131444121OAI: oai:DiVA.org:kth-314231DiVA, id: diva2:1671326
Note

QC 20220617

Available from: 2022-06-17 Created: 2022-06-17 Last updated: 2022-06-25Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Adler, JonasVerdier, OlivierÖktem, Ozan

Search in DiVA

By author/editor
Adler, JonasVerdier, OlivierÖktem, Ozan
By organisation
Mathematics (Div.)
In the same journal
Inverse Problems
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 137 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf