Data augmentation (DA) is a universal technique to reduce overfitting and improve the robustness of machine learning models by increasing quantity variety training dataset. Although data essential in vision tasks, it rarely applied text datasets since less straightforward. Some studies have concerned augmentation, but most them are for majority languages, such as English or French. There been o...

A novel data augmentation method suitable for wearable sensor data is proposed. Although numerous studies have revealed the importance of the data augmentation to improve the accuracy and robustness in machine-learning tasks, the data augmentation method that is applicable to wearable sensor data have not been well studied. Unlike the conventional data augmentation methods, which are mainly dev...

In this paper, we present a data augmentation method that generates synthetic medical images using Generative Adversarial Networks (GANs). We propose a training scheme that first uses classical data augmentation to enlarge the training set and then further enlarges the data size and its diversity by applying GAN techniques for synthetic data augmentation. Our method is demonstrated on a limited...

background breast augmentation is the most frequent procedure performed according to the 2009 quick facts report of the american society of plastic surgeons. this study presents the periareolar extra-glandular breast augmentation. methods from 2004 to 2010 among 32 female patients, peri-areolar incision was performed for breast augmentation. dissection was performed in subcutaneous plane toward...

introduction here we report an unusual case of massive stone formation in augmented urinary bladder. case presentation a 25-year-old man presented with recurrent urinary tract infection ten years after augmentation cystoplasty after a complex pelvic fracture urethral distraction defect. on evaluation by ultrasonography, x-ray, and computed tomography of abdomen showed large burden of stones in ...

Data augmentation, a technique in which a training set is expanded with class-preserving transformations, is ubiquitous in modern machine learning pipelines. In this paper, we seek to establish a theoretical framework for understanding modern data augmentation techniques. We start by showing that for kernel classifiers, data augmentation can be approximated by first-order feature averaging and ...