InAugment: Improving Classifiers via Internal Augmentation

Moab Arar, Ariel Shamir, Amit Bermano

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Image augmentation techniques apply transformation functions such as rotation, shearing, or color distortion on an input image. These augmentations were proven useful in improving neural networks' generalization ability. In this paper, we present a novel augmentation operation, In-Augment, that exploits image internal statistics. The key idea is to copy patches from the image itself, apply augmentation operations on them, and paste them back at random positions on the same image. This method is simple and easy to implement and can be incorporated with existing augmentation techniques. We test InAugment on two popular datasets - CIFAR and ImageNet. We show improvement over state-of-the-art augmentation techniques. Incorporating InAugment with Auto Augment yields a significant improvement over other augmentation techniques (e.g., +1% improvement over multiple architectures trained on the CIFAR dataset). We also demonstrate an increase for ResNet50 and EfficientNet-B3 top-1's accuracy on the ImageNet dataset compared to prior augmentation methods. Finally, our experiments suggest that training convolutional neural network using InAugment not only improves the model's accuracy and confidence but its performance on out-of-distribution images.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1698-1707
Number of pages10
ISBN (Electronic)9781665401913
DOIs
StatePublished - 2021
Event18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021 - Virtual, Online, Canada
Duration: 11 Oct 202117 Oct 2021

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2021-October
ISSN (Print)1550-5499

Conference

Conference18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
Country/TerritoryCanada
CityVirtual, Online
Period11/10/2117/10/21

Fingerprint

Dive into the research topics of 'InAugment: Improving Classifiers via Internal Augmentation'. Together they form a unique fingerprint.

Cite this