A survey on Image Data Augmentation for Deep Learning

@article{Shorten2019ASO,
  title={A survey on Image Data Augmentation for Deep Learning},
  author={Connor Shorten and Taghi M. Khoshgoftaar},
  journal={Journal of Big Data},
  year={2019},
  volume={6},
  pages={1-48}
}
Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. Overfitting refers to the phenomenon when a network learns a function with very high variance such as to perfectly model the training data. Unfortunately, many application domains do not have access to big data, such as medical image analysis. This survey focuses on Data Augmentation, a data-space solution to the problem… Expand
A review of medical image data augmentation techniques for deep learning applications
TLDR
A systematic review of the literature where data augmentation was utilised on medical images to train a deep learning model aims to give an insight to these techniques and confidence in the validity of the models produced. Expand
A comprehensive survey of recent trends in deep learning for digital images augmentation
TLDR
The current image data augmentation techniques which can be used to increase the number of images are delivered and discussed and the state of the art of using image data Augmentation techniques in the different deep learning research and application is surveyed. Expand
Data augmentation for deep learning based accelerated MRI reconstruction with limited data
TLDR
The DA pipeline, MRAugment, is specifically designed to utilize the invariances present in medical imaging measurements as naive DA strategies that neglect the physics of the problem fail, and demonstrates that in the low-data regime DA prevents overfitting and can match or even surpass the state of the art while using significantly fewer training data. Expand
SpeckleGAN: a generative adversarial network with an adaptive speckle layer to augment limited training data for ultrasound image processing
  • L. Bargsten, A. Schlaefer
  • Computer Science, Medicine
  • International Journal of Computer Assisted Radiology and Surgery
  • 2020
TLDR
A new algorithm for generation of synthetic medical images exhibiting speckle noise via generative adversarial networks (GANs) that facilitates the generation of realistic synthetic ultrasound images to augment small training sets for deep learning based image processing. Expand
Artificial MRI Image Generation using Deep Convolutional GAN and its Comparison with other Augmentation Methods
  • Rejusha T R, Vipin Kumar K S
  • Computer Science
  • 2021 International Conference on Communication, Control and Information Sciences (ICCISc)
  • 2021
TLDR
This paper aims to discuss some of the recent approaches of data augmentation that can be used to generate artificial brain MRI images for the detection of Alzheimer's Disease and the useful aspects of the different augmentation methods used. Expand
Enhancing Performance of Deep Learning Models with different Data Augmentation Techniques: A Survey
  • Cherry Khosla, B. Saini
  • Computer Science
  • 2020 International Conference on Intelligent Engineering and Management (ICIEM)
  • 2020
TLDR
This survey paper focuses on different data augmentation techniques based on data warping and oversampling and gives a brief discussion on different solutions of reducing the overfitting problem. Expand
Medical Image Synthetic Data Augmentation Using GAN
TLDR
Experimental results show that the data synthesized by this synthetic data augmentation method is better than existing methods and aims to solve the problem that deep neural networks are difficult to train on small-scale medical image datasets. Expand
Data Augmentation using Adversarial Networks for Tea Diseases Detection
TLDR
Generative adversarial networks (GAN) and deep convolutional GAN (DCGAN) are used for data augmentation for diseases detection and experimental results indicate that the highest GAN accuracy is obtained by DenseNet architecture. Expand
StyleGANs and Transfer Learning for Generating Synthetic Images in Industrial Applications
TLDR
This paper evaluates a StyleGAN generative model with transfer learning on different application domains—training with paintings, portraits, Pokémon, bedrooms, and cats—to generate target images with different levels of content variability and found that StyleGAN with transferLearning produced good quality images. Expand
Fast Mesh Data Augmentation via Chebyshev Polynomial of Spectral filtering
TLDR
This study proposed two unbiased augmentation methods, Laplace-Beltrami eigenfunction DataAugmentation (LB-eigDA) and Chebyshev polynomial Data Augmentation (C-pDA), to generate new data on surfaces, whose mean was the same as that of observed data. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 158 REFERENCES
Data augmentation for improving deep learning in image classification problem
TLDR
This paper has compared and analyzed multiple methods of data augmentation in the task of image classification, starting from classical image transformations like rotating, cropping, zooming, histogram based methods and finishing at Style Transfer and Generative Adversarial Networks, along with the representative examples. Expand
Improving Deep Learning using Generic Data Augmentation
TLDR
Experimental results, run using 4-fold cross-validation and reported in terms of Top-1 and Top-5 accuracy, indicate that cropping in geometric augmentation significantly increases CNN task performance. Expand
Research on data augmentation for image classification based on convolution neural networks
TLDR
Experimental results show that, under the same condition of multiple increasing, the performance evaluation on small-scale data sets is more obvious, the four individual methods perform generally better than others, and some appropriate combination methods are slightly more effective than the individuals. Expand
GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
TLDR
It is shown that generated medical images can be used for synthetic data augmentation, and improve the performance of CNN for medical image classification, and generalize to other medical classification applications and thus support radiologists’ efforts to improve diagnosis. Expand
Data Augmentation Using Random Image Cropping and Patching for Deep CNNs
TLDR
A new data augmentation technique called random image cropping and patching (RICAP) which randomly crops four images and patches them to create a new training image and achieves a new state-of-the-art test error of 2.19% on CIFAR-10. Expand
Chest x-ray generation and data augmentation for cardiovascular abnormality classification
TLDR
This work investigates the use of GANs for producing chest X-ray images to augment a dataset and uses this dataset to train a convolutional neural network to classify images for cardiovascular abnormalities. Expand
Data Augmentation for Skin Lesion Analysis
TLDR
The results confirm the importance of data augmentation in both training and testing and show that it can lead to more performance gains than obtaining new images. Expand
Biomedical Data Augmentation Using Generative Adversarial Neural Networks
TLDR
This work proposes a new application of GANNs to the automatic generation of artificial Magnetic Resonance Images (MRI) of slices of the human brain; both quantitative and human-based evaluations of generated images have been carried out in order to assess effectiveness of the method. Expand
The Effectiveness of Data Augmentation in Image Classification using Deep Learning
TLDR
A method to allow a neural net to learn augmentations that best improve the classifier, which is called neural augmentation is proposed, and the successes and shortcomings of this method are discussed. Expand
DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification
TLDR
A new discriminator loss is proposed to fit the goal of data augmentation, through which both real and augmented samples are enforced to contribute to and be consistent in finding the decision boundaries. Expand
...
1
2
3
4
5
...