Albumentations: Fast and Flexible Image Augmentations

Data augmentation is a commonly used technique for increasing both the size and the diversity of labeled training sets by leveraging input transformations that preserve corresponding output labels. In computer vision, image augmentations have become a common implicit regularization technique to comb...

Full description

Saved in:
Bibliographic Details
Published in:Information (Basel) Vol. 11; no. 2; p. 125
Main Authors: Buslaev, Alexander, Iglovikov, Vladimir I., Khvedchenya, Eugene, Parinov, Alex, Druzhinin, Mikhail, Kalinin, Alexandr A.
Format: Journal Article
Language:English
Published: Basel MDPI AG 01.02.2020
Subjects:
Algorithms
Application programming interface
Classification
Computer vision
Data augmentation
Datasets
Deep learning
Image processing
Libraries
Machine learning
Neural networks
Performance enhancement
Recipes
Regularization
Software
ISSN:2078-2489, 2078-2489
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Data augmentation is a commonly used technique for increasing both the size and the diversity of labeled training sets by leveraging input transformations that preserve corresponding output labels. In computer vision, image augmentations have become a common implicit regularization technique to combat overfitting in deep learning models and are ubiquitously used to improve performance. While most deep learning frameworks implement basic image transformations, the list is typically limited to some variations of flipping, rotating, scaling, and cropping. Moreover, image processing speed varies in existing image augmentation libraries. We present Albumentations, a fast and flexible open source library for image augmentation with many various image transform operations available that is also an easy-to-use wrapper around other augmentation libraries. We discuss the design principles that drove the implementation of Albumentations and give an overview of the key features and distinct capabilities. Finally, we provide examples of image augmentations for different computer vision tasks and demonstrate that Albumentations is faster than other commonly used image augmentation tools on most image transform operations.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2078-2489
2078-2489
DOI:10.3390/info11020125