State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's generalizability in the limited-label regime. Semi-supervised learning and unsupervised learning offer promising paradigms to learn from an abundance of unlabeled visual data. Recent progress in these paradigms has indicated the strong benefits of leveraging unlabeled data to improve model generalization and provide better model initialization. In this survey, we review the recent advanced deep learning algorithms on semi-supervised learning (SSL) and unsupervised learning (UL) for visual recognition from a unified perspective. To offer a holistic understanding of the state-of-the-art in these areas, we propose a unified taxonomy. We categorize existing representative SSL and UL with comprehensive and insightful analysis to highlight their design rationales in different learning scenarios and applications in different computer vision tasks. Lastly, we discuss the emerging trends and open challenges in SSL and UL to shed light on future critical research directions.

Semi-Supervised and Unsupervised Deep Visual Learning: A Survey / Chen, Yanbei; Mancini, Massimiliano; Zhu, Xiatian; Akata, Zeynep. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 46:3(2024), pp. 1327-1347. [10.1109/tpami.2022.3201576]

Semi-Supervised and Unsupervised Deep Visual Learning: A Survey

Mancini, Massimiliano;
2024-01-01

Abstract

State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's generalizability in the limited-label regime. Semi-supervised learning and unsupervised learning offer promising paradigms to learn from an abundance of unlabeled visual data. Recent progress in these paradigms has indicated the strong benefits of leveraging unlabeled data to improve model generalization and provide better model initialization. In this survey, we review the recent advanced deep learning algorithms on semi-supervised learning (SSL) and unsupervised learning (UL) for visual recognition from a unified perspective. To offer a holistic understanding of the state-of-the-art in these areas, we propose a unified taxonomy. We categorize existing representative SSL and UL with comprehensive and insightful analysis to highlight their design rationales in different learning scenarios and applications in different computer vision tasks. Lastly, we discuss the emerging trends and open challenges in SSL and UL to shed light on future critical research directions.
2024
3
Chen, Yanbei; Mancini, Massimiliano; Zhu, Xiatian; Akata, Zeynep
Semi-Supervised and Unsupervised Deep Visual Learning: A Survey / Chen, Yanbei; Mancini, Massimiliano; Zhu, Xiatian; Akata, Zeynep. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 46:3(2024), pp. 1327-1347. [10.1109/tpami.2022.3201576]
File in questo prodotto:
File Dimensione Formato  
Semi-Supervised_and_Unsupervised_Deep_Visual_Learning_A_Survey.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 4.07 MB
Formato Adobe PDF
4.07 MB Adobe PDF Visualizza/Apri
Semi-Supervised_and_Unsupervised_Deep_Visual_Learning_A_Survey.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 3.35 MB
Formato Adobe PDF
3.35 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/400766
Citazioni
  • ???jsp.display-item.citation.pmc??? 4
  • Scopus 27
  • ???jsp.display-item.citation.isi??? 51
  • OpenAlex ND
social impact