A survey on Image Data Augmentation for Deep Learning

  title={A survey on Image Data Augmentation for Deep Learning},
  author={Connor Shorten and Taghi M. Khoshgoftaar},
  journal={Journal of Big Data},
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… 

GAN augmentation for multiclass image classification using hemorrhage detection as a case-study

This work designs conditional DCGAN (cDCGAN) and in parallel trained multiple popular GAN models to use as online augmentations and compared them to traditional augmentation methods for the hemorrhage case study, showing that for complex and imbalanced datasets, traditional data imbalancing solutions may not be sufficient and require more complex and diverse data augmentation Methods to solve.

How to increase and balance current DBT datasets via an Evolutionary GAN: preliminary results

This work explores the use of GAN networks on Digital Breast Tomosynthe-sis (DBT) images, which is, in the knowledge, a completely new approach in this domain, and applies an optimization approach to the learning process of GAn networks based on evolutionary techniques.

Survey on Videos Data Augmentation for Deep Learning Models

The aim of this paper is to perform an exhaustive study of the novel techniques of video data augmentation for Deep Learning models and to point out the future directions of the research on this topic.

A review of medical image data augmentation techniques for deep learning applications

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.

Feature transforms for image data augmentation

A problem with convolutional neural networks (CNNs) is that they require large datasets to obtain adequate robustness; on small datasets, they are prone to overfitting. Many methods have been

Empirical Evaluation of the Effectiveness of Variational Autoencoders on Data Augmentation for the Image Classification Problem

This study evaluates the effectiveness of a generative model, variational autoencoders (VAE), on the image classification problem and observes that the contribution of data augmentation is sensitive to the size of the dataset and VAE augmented is as effective as the transformation based augmentation methods.

Data augmentation for deep learning based accelerated MRI reconstruction with limited data

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.

Endoscopic Image Analysis Using Deep Convolutional GAN And Traditional Data Augmentation

This work has applied traditional data augmentation and Generative Adversarial Network (GAN) on endoscopic esophagus images to increase the number of images for the training datasets, which have not yet been explored in literature.

A generative adversarial network for synthetization of regions of interest based on digital mammograms

A GAN model, named ROImammoGAN, which synthesizes ROI-based digital mammograms and performs competitively with state-of-the-art GANs for augmenting CNN models withROI-centric image samples for the characterization of abnormalities in breast images is proposed.

SpeckleGAN: a generative adversarial network with an adaptive speckle layer to augment limited training data for ultrasound image processing

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.



Data augmentation for improving deep learning in image classification problem

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.

Research on data augmentation for image classification based on convolution neural networks

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.

Data Augmentation Using Random Image Cropping and Patching for Deep CNNs

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.

Chest x-ray generation and data augmentation for cardiovascular abnormality classification

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.

Data Augmentation for Skin Lesion Analysis

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.

The Effectiveness of Data Augmentation in Image Classification using Deep Learning

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.

Biomedical Data Augmentation Using Generative Adversarial Neural Networks

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.

Learning from Simulated and Unsupervised Images through Adversarial Training

This work develops a method for S+U learning that uses an adversarial network similar to Generative Adversarial Networks (GANs), but with synthetic images as inputs instead of random vectors, and makes several key modifications to the standard GAN algorithm to preserve annotations, avoid artifacts, and stabilize training.

DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification

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.