Consequential Advancements of Self-Supervised Learning (SSL) in Deep Learning Contexts

被引:19
作者
Abdulrazzaq, Mohammed Majid [1 ,2 ]
Ramaha, Nehad T. A. [1 ]
Hameed, Alaa Ali [3 ]
Salman, Mohammad [4 ]
Yon, Dong Keon [5 ]
Fitriyani, Norma Latif [6 ]
Syafrudin, Muhammad [6 ]
Lee, Seung Won [7 ]
机构
[1] Karabuk Univ, Dept Comp Engn, Demir Celik Campus, TR-78050 Karabuk, Turkiye
[2] Univ Anbar, Renewable Energy Res Ctr, Ramadi 31001, Iraq
[3] Istinye Univ, Fac Engn & Nat Sci, Dept Comp Engn, TR-34396 Istanbul, Turkiye
[4] American Univ Middle East, Coll Engn & Technol, Egaila 54200, Kuwait
[5] Kyung Hee Univ, Med Sci Res Inst, Ctr Digital Hlth, Med Ctr, Seoul, South Korea
[6] Sejong Univ, Dept Artificial Intelligence, Seoul 05006, South Korea
[7] Sungkyunkwan Univ, Sch Med, Dept Precis Med, Suwon 16419, South Korea
基金
新加坡国家研究基金会;
关键词
deep learning (DL); self-supervised learning (SSL); machine learning (ML); cognition; classification; data annotation; DIAGNOSIS; NETWORK; MODEL;
D O I
10.3390/math12050758
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Self-supervised learning (SSL) is a potential deep learning (DL) technique that uses massive volumes of unlabeled data to train neural networks. SSL techniques have evolved in response to the poor classification performance of conventional and even modern machine learning (ML) and DL models of enormous unlabeled data produced periodically in different disciplines. However, the literature does not fully address SSL's practicalities and workabilities necessary for industrial engineering and medicine. Accordingly, this thorough review is administered to identify these prominent possibilities for prediction, focusing on industrial and medical fields. This extensive survey, with its pivotal outcomes, could support industrial engineers and medical personnel in efficiently predicting machinery faults and patients' ailments without referring to traditional numerical models that require massive computational budgets, time, storage, and effort for data annotation. Additionally, the review's numerous addressed ideas could encourage industry and healthcare actors to take SSL principles into an agile application to achieve precise maintenance prognostics and illness diagnosis with remarkable levels of accuracy and feasibility, simulating functional human thinking and cognition without compromising prediction efficacy.
引用
收藏
页数:42
相关论文
共 145 条
[1]   Self-Supervised Learning for data scarcity in a fatigue damage prognostic problem [J].
Akrim, Anass ;
Gogu, Christian ;
Vingerhoeds, Rob ;
Salaun, Michel .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 120
[2]   Few-shot symbol classification via self-supervised learning and nearest neighbor [J].
Alfaro-Contreras, Maria ;
Rios-Vila, Antonio ;
Valero-Mas, Jose J. ;
Calvo-Zaragoza, Jorge .
PATTERN RECOGNITION LETTERS, 2023, 167 :1-8
[3]   Big Self-Supervised Models Advance Medical Image Classification [J].
Azizi, Shekoofeh ;
Mustafa, Basil ;
Ryan, Fiona ;
Beaver, Zachary ;
Freyberg, Jan ;
Deaton, Jonathan ;
Loh, Aaron ;
Karthikesalingam, Alan ;
Kornblith, Simon ;
Chen, Ting ;
Natarajan, Vivek ;
Norouzi, Mohammad .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :3458-3468
[4]  
Bachman P, 2019, ADV NEUR IN, V32
[5]   Self-supervised deep geometric subspace clustering network [J].
Baek, Sangwon ;
Yoon, Gangjoon ;
Song, Jinjoo ;
Yoon, Sang Min .
INFORMATION SCIENCES, 2022, 610 :235-245
[6]  
Baevski Alexei, P MACHINE LEARNING R
[7]  
Balestriero R, 2023, Arxiv, DOI [arXiv:2304.12210, DOI 10.48550/ARXIV.2304.12210]
[8]  
Bardes A, 2022, Arxiv, DOI [arXiv:2105.04906, DOI 10.48550/ARXIV.2105.04906]
[9]   Self-Supervised Learning for Scene Classification in Remote Sensing: Current State of the Art and Perspectives [J].
Berg, Paul ;
Minh-Tan Pham ;
Courty, Nicolas .
REMOTE SENSING, 2022, 14 (16)
[10]   Self-Supervised Learning for Precise Pick-and-Place Without Object Model [J].
Berscheid, Lars ;
Meissner, Pascal ;
Kroger, Torsten .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2020, 5 (03) :4828-4835