Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Enhancing Electron Microscopy Image Classification Using Data Augmentation

Conference ·

Manual labeling for machine learning tasks such as image classification is tedious and labor-intensive; as a result, scientific datasets suitable for deep learning applications are scarce and limited. While data augmentation techniques have shown promise for extending image datasets, very little work has been done to understand the impact of combining multiple augmentation methods sequentially or the limits of their effectiveness when combined. Our work addresses this gap by examining how standard and combinatorial data augmentation affects the performance of machine learning models when trained on small datasets for label classification tasks. For our analysis, we generate single, double and quadruple-augmented datasets for a microscopy image classification task using six standard augmentation methods, and compare the resultant improvements observed in binary classification accuracy with three standard image classification models (DenseNet169, MobileNetV2, ResNet101V2). Our experiments show a non-monotonic relationship between the number of simultaneous augmentation methods and classification accuracy, indicating that there is a trade-off between the degree of augmentation and the model performance. These findings suggest that the optimal number of augmentation methods will vary by domain and use case. We also find that the order in which augmentation methods are applied to a limited dataset matters when combining augmentation schemes, with our use case showing performance differences up to 2.6% when the augmentation order is reversed for double-augmented datasets. Our work offers insights to the limits of data augmentation when working on image classification tasks with limited datasets.

Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
DOE Contract Number:
AC02-05CH11231
OSTI ID:
2525894
Country of Publication:
United States
Language:
English

References (11)

Effect of data-augmentation on fine-tuned CNN model performance journal March 2021
Data augmentation for improving deep learning in image classification problem conference May 2018
Understanding Data Augmentation for Classification: When to Warp? conference November 2016
ScienceSearch: Enabling Search through Automatic Metadata Generation conference October 2018
A survey on Image Data Augmentation for Deep Learning journal July 2019
Automated Labeling of Electron Microscopy Images Using Deep Learning conference November 2018
Identity Mappings in Deep Residual Networks book January 2016
Data augmentation in microscopic images for material data mining journal August 2020
Best practices for convolutional neural networks applied to visual document analysis conference January 2003
Assessing the impact of data augmentation and a combination of CNNs on leukemia classification journal September 2022
TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation conference October 2021

Similar Records

Deep learning with mixup augmentation for improved pore detection during additive manufacturing
Technical Report · Tue Jun 11 00:00:00 EDT 2024 · OSTI ID:2377316

Related Subjects