Related papers: DADA: Deep Adversarial Data Augmentation for Extre…

Optimization of image transformation functions for the purpose of data augmentation has been intensively studied. In particular, adversarial data augmentation strategies, which search augmentation maximizing task loss, show significant…

Deep learning-based methods have reached state of the art performances, relying on large quantity of available data and computational power. Such methods still remain highly inappropriate when facing a major open machine learning problem,…

Pretrained language models (PLMs) perform poorly under adversarial attacks. To improve the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted to cover more search space of adversarial attacks by adding…

Deep learning (DL) algorithms have shown significant performance in various computer vision tasks. However, having limited labelled data lead to a network overfitting problem, where network performance is bad on unseen data as compared to…

Recent domain adaptation methods have demonstrated impressive improvement on unsupervised domain adaptation problems. However, in the semi-supervised domain adaptation (SSDA) setting where the target domain has a few labeled instances…

A generative adversarial network (GAN)-based vocoder trained with an adversarial discriminator is commonly used for speech synthesis because of its fast, lightweight, and high-quality characteristics. However, this data-driven model…

Lithography modeling is a crucial problem in chip design to ensure a chip design mask is manufacturable. It requires rigorous simulations of optical and chemical models that are computationally expensive. Recent developments in machine…

Deep Neural Networks (DNNs) have improved the accuracy of classification problems in lots of applications. One of the challenges in training a DNN is its need to be fed by an enriched dataset to increase its accuracy and avoid it suffering…

Discriminator plays a vital role in training generative adversarial networks (GANs) via distinguishing real and synthesized samples. While the real data distribution remains the same, the synthesis distribution keeps varying because of the…

Sufficient supervised information is crucial for any machine learning models to boost performance. However, labeling data is expensive and sometimes difficult to obtain. Active learning is an approach to acquire annotations for data from a…

Convolutional Neural Network (CNN)-based accurate prediction typically requires large-scale annotated training data. In Medical Imaging, however, both obtaining medical data and annotating them by expert physicians are challenging; to…

Recent deep networks achieved state of the art performance on a variety of semantic segmentation tasks. Despite such progress, these models often face challenges in real world `wild tasks' where large difference between labeled…

Data augmentation is a widely used technique in classification to increase data used in training. It improves generalization and reduces amount of annotated human activity data needed for training which reduces labour and time needed with…

Unsupervised Data Augmentation (UDA) is a semi-supervised technique that applies a consistency loss to penalize differences between a model's predictions on (a) observed (unlabeled) examples; and (b) corresponding 'noised' examples produced…

Data augmentation is a key tool for improving the performance of deep networks, particularly when there is limited labeled data. In some fields, such as computer vision, augmentation methods have been extensively studied; however, for…

Data augmentation is essential to achieve state-of-the-art performance in many deep learning applications. However, the most effective augmentation techniques become computationally prohibitive for even medium-sized datasets. To address…

The quality and size of training set have great impact on the results of deep learning-based face related tasks. However, collecting and labeling adequate samples with high quality and balanced distributions still remains a laborious and…

Generative Adversarial Networks (GANs) are a popular formulation to train generative models for complex high dimensional data. The standard method for training GANs involves a gradient descent-ascent (GDA) procedure on a minimax…

In many practical applications, it is often difficult and expensive to obtain large-scale labeled data to train state-of-the-art deep neural networks. Therefore, transferring the learned knowledge from a separate, labeled source domain to…

Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks. These networks are often trained end-to-end to directly reconstruct an image from a noisy or corrupted measurement of that image. To…