Abstract

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.

Affiliated Institutions

Related Publications

Publication Info

Year
2020
Type
article
Volume
11
Issue
2
Pages
125-125
Citations
1852
Access
Closed

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1852
OpenAlex
94
Influential
1845
CrossRef

Cite This

Alexander Buslaev, Vladimir I. Iglovikov, Eugene Khvedchenya et al. (2020). Albumentations: Fast and Flexible Image Augmentations. Information , 11 (2) , 125-125. https://doi.org/10.3390/info11020125

Identifiers

DOI
10.3390/info11020125
arXiv
1809.06839

Data Quality

Data completeness: 79%