A Survey on Semi-, Self- and Unsupervised Learning for Image Classification

While deep learning strategies achieve outstanding results in computer vision tasks, one issue remains: The current strategies rely heavily on a huge amount of labeled data. In many real-world problems, it is not feasible to create such an amount of labeled training data. Therefore, it is common to...

Full description

Saved in:
Bibliographic Details
Published inIEEE access Vol. 9; pp. 82146 - 82168
Main Authors Schmarje, Lars, Santarossa, Monty, Schroder, Simon-Martin, Koch, Reinhard
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Clusters
Computer vision
Deep learning
Image classification
Labels
Machine learning
Measurement
Robustness (mathematics)
self-supervised
Semi-supervised
Supervised learning
survey
Task analysis
Taxonomy
Training
unsupervised
Unsupervised learning
Online AccessGet full text

Cover

More Information
Summary:While deep learning strategies achieve outstanding results in computer vision tasks, one issue remains: The current strategies rely heavily on a huge amount of labeled data. In many real-world problems, it is not feasible to create such an amount of labeled training data. Therefore, it is common to incorporate unlabeled data into the training process to reach equal results with fewer labels. Due to a lot of concurrent research, it is difficult to keep track of recent developments. In this survey, we provide an overview of often used ideas and methods in image classification with fewer labels. We compare 34 methods in detail based on their performance and their commonly used ideas rather than a fine-grained taxonomy. In our analysis, we identify three major trends that lead to future research opportunities. 1. State-of-the-art methods are scalable to real-world applications in theory but issues like class imbalance, robustness, or fuzzy labels are not considered. 2. The degree of supervision which is needed to achieve comparable results to the usage of all labels is decreasing and therefore methods need to be extended to settings with a variable number of classes. 3. All methods share some common ideas but we identify clusters of methods that do not share many ideas. We show that combining ideas from different clusters can lead to better performance.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2021.3084358