The Effect of Data Augmentation on the Performance of Convolutional Neural Networks

Abstract

Soft biometrics classification has been gaining acceptance during the recent years for critical applications, mainly in the security field. Recognizing individuals by using only behavioral, physical or psychological characteristics is a task that can be helpful for several purposes. Thus, different Deep Learning approaches have been proposed to perform this task. Since these methods require a large amount of data to avoid overfitting, data augmentation is a commonly used method. However, its isolated effect on the performance of the models are usually not evaluated. This work aims at studying the effect of different data augmentation strategies on the performances of two Convolutional Neural Network architectures for classifying soft biometrics attributes from samples of a novel dataset: LABICv1.Recently, several works appeared, aiming at solving this problem through different strategies, usually Deep Learning (DL) [2] approaches such as Convolutional Neural Networks (CNNs) [3]. For instance, Perlin and Lopes [4] presented two CNNs with the same architecture but with different operation modes: one for classifying three soft biometrics (Upper Clothes, Lower Clothes and Gender) at once and the other for classifying a single soft biometric. The first was trained using the negative log-likelihood as loss function and the second with the mean squared error. In the work presented by Levi and Hassncer [5], age and gender of individuals were classified from images of human faces using a deep CNN, whilst Wang et al. [6] presented an approach based on a 6-layer architecture CNN for feature extraction, in order to estimate age from images containing faces. The works by Zhu et al. [7] and Martinho-Corbishley et al. [8] presented architectures based on slicing images of individuals and feeding each sliced window to different input layers of the network. Each input is propagated through separate Convolution and Pooling layers until reaching the Fully Connected layer, where the outputs of each layer are combined to form an unique flattened vector. Both approaches allow to perform multi-label classification. All works used variations of the Stochastic Gradient Descent (SGD) method [9].Since DL models require a large amount of data to obtain satisfactory results and soft biometrics datasets are usually small, the use of data augmentation is common to reduce overfitting and improve the classification performance [10,11]. This method is based on generating new samples of the original dataset by applying small random transformations to the original samples, whilst preserving their labels. Works related to soft biometrics classification are often focused on the architecture of the model without evaluating the particular isolated effect of data augmentation.This work presents a study regarding the effect of data augmentation on the performance of CNN architectures with different complexities for a small dataset (which can also be unbalanced depending on the attribute to classify). For this purpose, we present a new labeled dataset f...

Prediction of critical temperature and new superconducting materials

“…This is due to the fact that a simpler linear regression method allows to describe well only linear dependencies, and according to [13], a strong linear dependence of the features on the critical temperature was not found, which makes this method not applicable. Neural networks were not used as a model since the quality and implementation of this method strongly depends on the size of the data [17,18], which in this paper is not enough to implement this method. The feature selection algorithm, which is used in the work, largely repeats the ADD-DEL procedure [19], except that at each iteration the selected feature is added or deleted, not to achieve the greatest improvement of the model among all the features at this iteration, and the condition for improvement or deterioration is checked models.…”

Designing an Adaptive Age-Invariant Face Recognition System for Enhanced Security in Smart Urban Environments

“…Data augmentation is the process of adding noise to photos in order to boost the quantities [24]. The idea of data augmentation has a long history in literature and everyday life [25][26][27][28][29][30][31]. As a result, we were able to collect a pre-processed FG-NET dataset that included 5010 total face photos and an average of 60 face images per person.…”

Analysis and Mitigation of the Imbalance Impact on an Industrial Image Classification Dataset

“…Data augmentation is a compelling method to reduce overfitting problems [12]. Data augmentation introduces artificial images to the dataset by either warping or oversampling.…”