Data augmentation in microscopic images for material data mining
Authors:
- Xiaojuan BanXiaojuan Ban
- Haiyou HuangHaiyou Huang
- Stephen WuSWStephen Wu
- Adnan Omer AbuassbaAAAdnan Omer Abuassba
Preprint
Abstract
Recent progress in material data mining has been driven by high-capacity models trained on large datasets. However, collecting experimental data (real data) has been extremely costly since the amount of human effort and expertise required. Here, we develop a novel transfer learning strategy to address small or insufficient data problem. This strategy realizes the fusion of real and simulated data, and the augmentation of training data in data mining procedure. For a specific task of image segmentation, this strategy can generate synthetic images by fusing physical mechanism of simulated images and "image style" of real images. The result shows that the model trained with the acquired synthetic images and 35% of the real images outperforms the model trained on all real images. As the time required to generate synthetic data is almost negligible, this strategy is able to reduce the time cost of real data preparation by roughly 65%.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Predicting Materials Properties with Little Data Using Shotgun Transfer LearningACS Central Science, 2019
- Automated defect analysis in electron microscopic imagesnpj Computational Materials, 2018
- Playing for Data: Ground Truth from Computer Games2016
- Machine-learning-assisted materials discovery using failed experimentsNature, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Recent developments in advanced aircraft aluminium alloysMaterials & Design (1980-2015), 2014
- Future Directions in 3D Materials Science: Outlook from the First International Conference on 3D Materials ScienceJOM, 2014
- Microsoft COCO: Common Objects in Context2014
- Simulation of curvature-driven grain growth by using a modified monte carlo algorithmMetallurgical and Materials Transactions A, 1995
- Image Processing, Analysis and Machine Vision1993