Feature Learning-Based Generative Adversarial Network Data Augmentation for Class-Based Few-Shot Learning

Abstract

As training deep neural networks enough requires a large amount of data, there have been a lot of studies to deal with this problem. Data augmentation techniques are basic solutions to increase training data using existing data. Geometric transformations and color space augmentations are well-known augmentation techniques, but they still require some manual work and can generate limited types of data only. Therefore, there are many interests in generative-model-based augmentation lately, which can learn the distribution of data. This study proposes a set of GAN-based data augmentation methods that can generate good quality training data. The proposed networks, f-DAGAN (data augmentation generative adversarial networks), have been motivated by the DAGAN that learns data distribution from two real data. The basic f-DAGAN uses dual discriminators handling both generated data and generated feature spaces for better learning the given data. The other versions of f-DAGANs have been proposed for generating hard or easy data that have additional dual classifiers for both generated data and feature spaces to control the generator. Hard data is useful for optimized training to increase the target performance such as classification accuracy. Easy data generation can be used especially in few-shot learning. The quality of generated data has been validated in two ways: using t-SNE visualization of generated data and classification accuracy by training with generated data using the MNIST data set. The t-SNE representations show that data generated by f-DAGAN are evenly distributed for every class better than the exiting generative model-based augmentation methods. The f-DAGAN also shows the best classification accuracy by training with generated data. The f-DAGAN version for easy and hard data generation generates data well from five-shot learning and performs well in sample data generation experiments.

Computational and Mathematical Methods in Medicine Glioma Brain Tumor Detection and Classification Using Convolutional Neural Network

“…However, we made a comparative analysis between conventional machine learning and deep learning for experimental intention. Most of the experiments in conventional ML technique used support vector machine (SVM) [15] along with RDF kernel to make the reliable structure, the database learning technique consistent label (KSVD) [2], and the coactive adaptive neural fuzzy expert system (CANFES) [8], and finally, CNN is designed to automatically and adaptively learn spatial hierarchies of features through back-propagation by using multiple building blocks [11]. During the experiment, the statistical texture features like mean, median, contrast, energy, and variance have been utilized, and comparison outcome of deep learning base KSVD features, and we derive the features from CNN model GoogLeNet and may execute these outcomes on KSVD2.…”

“…Low-level time consumption for image analysis for the radiologist is very essential while addressing the issue, and it may have chances of increasing the life span of the victim. The proposed framework uses CNN for image analysis and classification operation [11]. These CNN-based classified images are important for clinicians to obtain higher precision and accuracy values.…”

Investigation of Applying Machine Learning and Hyperparameter Tuned Deep Learning Approaches for Arrhythmia Detection in ECG Images

“…Recent reviews unveil that the accuracy of the learned models may be improved by data augmentation. Data warping-based image augmentation is used in LeNet-5 [ 5 ], and it is the first application in which CNN is applied for handwritten digit classification. In [ 6 ], dataset size is increased by augmentation by applying cropping, flipping, and changing the intensity using PCA.…”

Analysis on COVID-19 Infection Spread Rate during Relief Schemes Using Graph Theory and Deep Learning

“…The image in Figure 3 shows how social distancing helps to control the spread of the infection by breaking the chain. There are few artificial intelligence (AI) based study on social distancing [10].…”