• Corpus ID: 152282791

Style transfer based data augmentation in material microscopic image processing

  title={Style transfer based data augmentation in material microscopic image processing},
  author={Boyuan Ma and Xiaoyan Wei and Chuni Liu and Xiao-juan Ban and Haiyou Huang and Hao Wang and Weihua Xue},
Recently progress in material microscopic image semantic segmentation has been driven by high-capacity models trained on large datasets. However, collecting microscopic images with pixel-level labels has been extremely costly due to the amount of human effort required. In this paper, we present an approach to rapidly creating microscopic images with pixel-level labels from material 3d simulated models. Usually images extracted directly from those 3d simulated models are not realistic enough. It… 


Image Style Transfer Using Convolutional Neural Networks
A Neural Algorithm of Artistic Style is introduced that can separate and recombine the image content and style of natural images and provide new insights into the deep image representations learned by Convolutional Neural Networks and demonstrate their potential for high level image synthesis and manipulation.
Playing for Data: Ground Truth from Computer Games
It is shown that associations between image patches can be reconstructed from the communication between the game and the graphics hardware, which enables rapid propagation of semantic labels within and across images synthesized by the game, with no access to the source code or the content.
Deep Learning-Based Image Segmentation for Al-La Alloy Microscopic Images
A deep learning-based method to address the task of image segmentation for microscopic images using an Al–La alloy that outperforms existing segmentation methods and achieves seamless segmentation.
Image Style Transfer using Convolutional Neural Networks
Recently there has been lots of progress in the field of image style transfer, a process which aims at redrawing an image in the style of another image. Gatys et al. proposed the first approach using
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
A Neural Algorithm of Artistic Style
This work introduces an artificial system based on a Deep Neural Network that creates artistic images of high perceptual quality and offers a path forward to an algorithmic understanding of how humans create and perceive artistic imagery.
Image-to-Image Translation with Conditional Adversarial Networks
Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
Automated defect analysis in electron microscopic images
Electron microscopy and defect analysis are a cornerstone of materials science, as they offer detailed insights on the microstructure and performance of a wide range of materials and material
Predicting Materials Properties with Little Data Using Shotgun Transfer Learning
To facilitate widespread use of transfer learning, a pretrained model library called XenonPy.MDL is developed, which comprises more than 140 000 pretrained models for various properties of small molecules, polymers, and inorganic crystalline materials and which has autonomously identified rather nontrivial transferability across different properties transcending the different disciplines of materials science.
Fully Convolutional Networks for Semantic Segmentation
It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.