Cargando…

Novel transfer learning schemes based on Siamese networks and synthetic data

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 applicat...

Descripción completa

Detalles Bibliográficos
Autores principales: Kenneweg, Philip, Stallmann, Dominik, Hammer, Barbara
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer London 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9757634/
https://www.ncbi.nlm.nih.gov/pubmed/36568475
http://dx.doi.org/10.1007/s00521-022-08115-2
_version_ 1784851862799777792
author Kenneweg, Philip
Stallmann, Dominik
Hammer, Barbara
author_facet Kenneweg, Philip
Stallmann, Dominik
Hammer, Barbara
author_sort Kenneweg, Philip
collection PubMed
description 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.
format Online
Article
Text
id pubmed-9757634
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Springer London
record_format MEDLINE/PubMed
spelling pubmed-97576342022-12-19 Novel transfer learning schemes based on Siamese networks and synthetic data Kenneweg, Philip Stallmann, Dominik Hammer, Barbara Neural Comput Appl Original Article 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. Springer London 2022-12-16 2023 /pmc/articles/PMC9757634/ /pubmed/36568475 http://dx.doi.org/10.1007/s00521-022-08115-2 Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Original Article
Kenneweg, Philip
Stallmann, Dominik
Hammer, Barbara
Novel transfer learning schemes based on Siamese networks and synthetic data
title Novel transfer learning schemes based on Siamese networks and synthetic data
title_full Novel transfer learning schemes based on Siamese networks and synthetic data
title_fullStr Novel transfer learning schemes based on Siamese networks and synthetic data
title_full_unstemmed Novel transfer learning schemes based on Siamese networks and synthetic data
title_short Novel transfer learning schemes based on Siamese networks and synthetic data
title_sort novel transfer learning schemes based on siamese networks and synthetic data
topic Original Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9757634/
https://www.ncbi.nlm.nih.gov/pubmed/36568475
http://dx.doi.org/10.1007/s00521-022-08115-2
work_keys_str_mv AT kennewegphilip noveltransferlearningschemesbasedonsiamesenetworksandsyntheticdata
AT stallmanndominik noveltransferlearningschemesbasedonsiamesenetworksandsyntheticdata
AT hammerbarbara noveltransferlearningschemesbasedonsiamesenetworksandsyntheticdata