A Survey on Long-Tailed Visual Recognition

The heavy reliance on data is one of the major reasons that currently limit the development of deep learning. Data quality directly dominates the effect of deep learning models, and the long-tailed distribution is one of the factors affecting data quality. The long-tailed phenomenon is prevalent due...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of computer vision Jg. 130; H. 7; S. 1837 - 1872
Hauptverfasser: Yang, Lu, Jiang, He, Song, Qing, Guo, Jun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.07.2022
Springer
Springer Nature B.V
Schlagworte:
Artificial Intelligence
Computational linguistics
Computer Imaging
Computer Science
Datasets
Deep learning
Image Processing and Computer Vision
Information management
Language processing
Laws, regulations and rules
Natural language interfaces
Pattern Recognition
Pattern Recognition and Graphics
Recognition
Survey Papers
Surveys
Vision
Deep learning
Long-tailed distribution
Gini coefficient
Visual recognition
ISSN:0920-5691, 1573-1405
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The heavy reliance on data is one of the major reasons that currently limit the development of deep learning. Data quality directly dominates the effect of deep learning models, and the long-tailed distribution is one of the factors affecting data quality. The long-tailed phenomenon is prevalent due to the prevalence of power law in nature. In this case, the performance of deep learning models is often dominated by the head classes while the learning of the tail classes is severely underdeveloped. In order to learn adequately for all classes, many researchers have studied and preliminarily addressed the long-tailed problem. In this survey, we focus on the problems caused by long-tailed data distribution, sort out the representative long-tailed visual recognition datasets and summarize some mainstream long-tailed studies. Specifically, we summarize these studies into ten categories from the perspective of representation learning, and outline the highlights and limitations of each category. Besides, we have studied four quantitative metrics for evaluating the imbalance, and suggest using the Gini coefficient to evaluate the long-tailedness of a dataset. Based on the Gini coefficient, we quantitatively study 20 widely-used and large-scale visual datasets proposed in the last decade, and find that the long-tailed phenomenon is widespread and has not been fully studied. Finally, we provide several future directions for the development of long-tailed learning to provide more ideas for readers.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-022-01622-8