基于Siamese网络和合成数据的迁移学习新方案。

IF 4.5 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Philip Kenneweg, Dominik Stallmann, Barbara Hammer
{"title":"基于Siamese网络和合成数据的迁移学习新方案。","authors":"Philip Kenneweg,&nbsp;Dominik Stallmann,&nbsp;Barbara Hammer","doi":"10.1007/s00521-022-08115-2","DOIUrl":null,"url":null,"abstract":"<p><p>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.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":null,"pages":null},"PeriodicalIF":4.5000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9757634/pdf/","citationCount":"1","resultStr":"{\"title\":\"Novel transfer learning schemes based on Siamese networks and synthetic data.\",\"authors\":\"Philip Kenneweg,&nbsp;Dominik Stallmann,&nbsp;Barbara Hammer\",\"doi\":\"10.1007/s00521-022-08115-2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>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.</p>\",\"PeriodicalId\":49766,\"journal\":{\"name\":\"Neural Computing & Applications\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.5000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9757634/pdf/\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neural Computing & Applications\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1007/s00521-022-08115-2\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Computing & Applications","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s00521-022-08115-2","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 1

摘要

基于深度网络的迁移学习方案已经在巨大的图像语料库上进行了训练,为计算机视觉提供了最先进的技术。在这里,监督和半监督方法构成了有效的技术,可以很好地处理相对较小的数据集。然而,这些应用目前仅限于适合深度网络模型的应用领域。在这篇文章中,我们讨论了生物技术领域的一个重要应用领域,微流控单细胞培养中CHO-K1悬浮液生长的自动分析,其中的数据特征与现有领域非常不同,训练好的深度网络不容易被经典迁移学习所适应。我们提出了一种新的迁移学习方案,该方案扩展了最近引入的基于真实和综合数据的Twin-VAE体系结构,并将其专门的训练过程修改为迁移学习领域。在特定的领域中,通常只有很少甚至没有标签,而且注释的成本很高。我们研究了一种新的迁移学习策略,该策略使用不变的共享表示以及合适的目标变量对自然和合成数据进行同步再训练,同时学习处理来自不同显微镜技术的未见数据。我们展示了Twin-VAE架构的变化在图像处理和经典图像处理技术中优于最先进的迁移学习方法的优势,即使在大大缩短训练时间的情况下,这种优势仍然存在,并在该领域取得了令人满意的结果。源代码可在https://github.com/dstallmann/transfer_learning_twinvae上获得,跨平台工作,是开源和免费(麻省理工学院许可)软件。我们在https://pub.uni-bielefeld.de/record/2960030上提供这些数据集。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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 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.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Neural Computing & Applications
Neural Computing & Applications 工程技术-计算机:人工智能
CiteScore
11.40
自引率
8.30%
发文量
1280
审稿时长
6.9 months
期刊介绍: Neural Computing & Applications is an international journal which publishes original research and other information in the field of practical applications of neural computing and related techniques such as genetic algorithms, fuzzy logic and neuro-fuzzy systems. All items relevant to building practical systems are within its scope, including but not limited to: -adaptive computing- algorithms- applicable neural networks theory- applied statistics- architectures- artificial intelligence- benchmarks- case histories of innovative applications- fuzzy logic- genetic algorithms- hardware implementations- hybrid intelligent systems- intelligent agents- intelligent control systems- intelligent diagnostics- intelligent forecasting- machine learning- neural networks- neuro-fuzzy systems- pattern recognition- performance measures- self-learning systems- software simulations- supervised and unsupervised learning methods- system engineering and integration. Featured contributions fall into several categories: Original Articles, Review Articles, Book Reviews and Announcements.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信