Please use this identifier to cite or link to this item: https://hdl.handle.net/10953/2337
Title: A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications.
Authors: Alzubaidi, L.
Bai, J.
Al-Sabaawi, A.
Santamaria, J.
Albahri, A.S.
Al-dabbagh, B.S.N.
Fadhel, M.A.
Manoufali, M.
Zhang, J.
Al-Timemy, A.H.
Duan, Y.
Abdullah, A.
Farhan, L.
Lu, Y.
Gupta, A.
Albu, F.
Abbosh, A.
Gu, Y.
Abstract: Data scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time‑consuming, and error‑prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also applica‑ tion dependent. This issue is the main barrier for many applications dismissing the use of DL. Having sufficient data is the first step toward any successful and trustworthy DL application. This paper presents a holistic survey on state‑of‑the‑art techniques to deal with training DL models to overcome three challenges including small, imbalanced datasets, and lack of generalization. This survey starts by listing the learning techniques. Next, the types of DL architectures are introduced. After that, state‑of‑the‑art solu‑ tions to address the issue of lack of training data are listed, such as Transfer Learning (TL), Self‑Supervised Learning (SSL), Generative Adversarial Networks (GANs), Model Architecture (MA), Physics‑Informed Neural Network (PINN), and Deep Synthetic Minor‑ ity Oversampling Technique (DeepSMOTE). Then, these solutions were followed by some related tips about data acquisition needed prior to training purposes, as well as recommendations for ensuring the trustworthiness of the training dataset. The survey ends with a list of applications that suffer from data scarcity, several alternatives are proposed in order to generate more data in each application including Electromag‑ netic Imaging (EMI), Civil Structural Health Monitoring, Medical imaging, Meteorol‑ ogy, Wireless Communications, Fluid Mechanics, Microelectromechanical system, and Cybersecurity. To the best of the authors’ knowledge, this is the first review that offers a comprehensive overview on strategies to tackle data scarcity in DL.
Keywords: Convolutional neural network
Deep Learning
Medical image analysis
Transfer learning
Issue Date: 14-Apr-2023
metadata.dc.description.sponsorship: The authors would like to acknowledge the support received through the following funding schemes of Australian Government: Australian Research Council (ARC) Industrial Transformation Training Centre (ITTC) for Joint Biomechanics under grant IC190100020. The authors also would like to acknowledge the support received through the MMPE ECR Ignition Grant, The Queensland University of Technology.
Publisher: Springer
Citation: Alzubaidi, L., Bai, J., Al-Sabaawi, A. et al. A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications. J Big Data 10, 46 (2023). https://doi.org/10.1186/s40537-023-00727-2
Appears in Collections:DI-Artículos

Files in This Item:
File Description SizeFormat 
s40537-023-00727-2.pdfFichero PDF5,01 MBAdobe PDFView/Open


This item is protected by original copyright