Multi-Label Active Learning Algorithms for Image Classification: Overview and Future Promise

Image classification is a key task in image understanding, and multi-label image classification has become a popular topic in recent years. However, the success of multi-label image classification is closely related to the way of constructing a training set. As active learning aims to construct an e...

Full description

Saved in:
Bibliographic Details
Published in:ACM computing surveys Vol. 53; no. 2
Main Authors: Wu, Jian, Sheng, Victor S, Zhang, Jing, Li, Hua, Dadakova, Tetiana, Swisher, Christine Leon, Cui, Zhiming, Zhao, Pengpeng
Format: Journal Article
Language:English
Published: United States 01.06.2020
Subjects:
annotation
active learning
Additional Key Words and Phrases
sampling strategy
multi-label image
Image classification
ISSN:0360-0300
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Image classification is a key task in image understanding, and multi-label image classification has become a popular topic in recent years. However, the success of multi-label image classification is closely related to the way of constructing a training set. As active learning aims to construct an effective training set through iteratively selecting the most informative examples to query labels from annotators, it was introduced into multi-label image classification. Accordingly, multi-label active learning is becoming an important research direction. In this work, we first review existing multi-label active learning algorithms for image classification. These algorithms can be categorized into two top groups from two aspects respectively: sampling and annotation. The most important component of multi-label active learning is to design an effective sampling strategy that actively selects the examples with the highest informativeness from an unlabeled data pool, according to various information measures. Thus, different informativeness measures are emphasized in this survey. Furthermore, this work also makes a deep investigation on existing challenging issues and future promises in multi-label active learning with a focus on four core aspects: example dimension, label dimension, annotation, and application extension.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0360-0300
DOI:10.1145/3379504