Novel transfer learning schemes based on Siamese networks and synthetic data

Kenneweg P, Stallmann D, Hammer B (2022)
Neural Computing and Applications 35: 8423–8436.

Zeitschriftenaufsatz | E-Veröff. vor dem Druck | Englisch
 
Download
OA 1.96 MB
Abstract / Bemerkung
Transfer learning schemes based on deep networks which have been trained on huge image corpora offer state-of-the-art technologies in computer vision. Here, supervised and semi-supervised approaches constitute efficient technologies which work well with comparably small data sets. Yet, such applications are currently restricted to application domains where suitable deep network models are readily available. In this contribution, we address an important application area in the domain of biotechnology, the automatic analysis of CHO-K1 suspension growth in microfluidic single-cell cultivation, where data characteristics are very dissimilar to existing domains and trained deep networks cannot easily be adapted by classical transfer learning. We propose a novel transfer learning scheme which expands a recently introduced Twin-VAE architecture, which is trained on realistic and synthetic data, and we modify its specialized training procedure to the transfer learning domain. In the specific domain, often only few to no labels exist and annotations are costly. We investigate a novel transfer learning strategy, which incorporates a simultaneous retraining on natural and synthetic data using an invariant shared representation as well as suitable target variables, while it learns to handle unseen data from a different microscopy technology. We show the superiority of the variation of our Twin-VAE architecture over the state-of-the-art transfer learning methodology in image processing as well as classical image processing technologies, which persists, even with strongly shortened training times and leads to satisfactory results in this domain. The source code is available at https://github.com/dstallmann/transfer_learning_twinvae, works cross-platform, is open-source and free (MIT licensed) software. We make the data sets available at https://pub.uni-bielefeld.de/record/2960030.
Erscheinungsjahr
2022
Zeitschriftentitel
Neural Computing and Applications
Band
35
Seite(n)
8423–8436
ISSN
0941-0643
eISSN
1433-3058
Finanzierungs-Informationen
Open-Access-Publikationskosten wurden durch die Universität Bielefeld im Rahmen des DEAL-Vertrags gefördert.
Page URI
https://pub.uni-bielefeld.de/record/2967683

Zitieren

Kenneweg P, Stallmann D, Hammer B. Novel transfer learning schemes based on Siamese networks and synthetic data. Neural Computing and Applications. 2022;35:8423–8436.
Kenneweg, P., Stallmann, D., & Hammer, B. (2022). Novel transfer learning schemes based on Siamese networks and synthetic data. Neural Computing and Applications, 35, 8423–8436. https://doi.org/10.1007/s00521-022-08115-2
Kenneweg, Philip, Stallmann, Dominik, and Hammer, Barbara. 2022. “Novel transfer learning schemes based on Siamese networks and synthetic data”. Neural Computing and Applications 35: 8423–8436.
Kenneweg, P., Stallmann, D., and Hammer, B. (2022). Novel transfer learning schemes based on Siamese networks and synthetic data. Neural Computing and Applications 35, 8423–8436.
Kenneweg, P., Stallmann, D., & Hammer, B., 2022. Novel transfer learning schemes based on Siamese networks and synthetic data. Neural Computing and Applications, 35, p 8423–8436.
P. Kenneweg, D. Stallmann, and B. Hammer, “Novel transfer learning schemes based on Siamese networks and synthetic data”, Neural Computing and Applications, vol. 35, 2022, pp. 8423–8436.
Kenneweg, P., Stallmann, D., Hammer, B.: Novel transfer learning schemes based on Siamese networks and synthetic data. Neural Computing and Applications. 35, 8423–8436 (2022).
Kenneweg, Philip, Stallmann, Dominik, and Hammer, Barbara. “Novel transfer learning schemes based on Siamese networks and synthetic data”. Neural Computing and Applications 35 (2022): 8423–8436.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung 4.0 International Public License (CC-BY 4.0):
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2022-12-19T10:28:10Z
MD5 Prüfsumme
be6b75627482a8524a87980486aef9f6


Link(s) zu Volltext(en)
Access Level
OA Open Access

Zitationen in Europe PMC

Daten bereitgestellt von Europe PubMed Central.

References

Daten bereitgestellt von Europe PubMed Central.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®
Quellen

PMID: 36568475
PubMed | Europe PMC

Suchen in

Google Scholar