Improving active learning by data balance to reduce annotation efforts

Improving active learning by data balance to reduce annotation efforts

Image classification is a fundamental task in image analysis. Recent advances in deep learning have achieved promising results on many image classification benchmarks. However, in some particular tasks, especially in biomedical image analysis, preparing a large number of labelled images for the mode...

Full description

Bibliographic Details
Main Authors: Han Lei, Shuai Wang, Dezhi Zheng, Xiaolei Qu, Shangchun Fan, Chongyang Cui
Format: Article
Language:English
Published: Wiley 2019-10-01
Series:The Journal of Engineering
Subjects:
pattern classification
learning (artificial intelligence)
neural nets
data balancing
deep learning
image classification benchmarks
biomedical image analysis
labelled images
annotated data
convolutional neural network
multiclass classification
binary natural dataset
biomedical dataset
improved active learning
Online Access:https://digital-library.theiet.org/content/journals/10.1049/joe.2018.9076

Similar Items

Similar Items