Related papers: Exploring Data Augmentations on Self-/Semi-/Fully-…
Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image…
Data augmentation is widely used as a part of the training process applied to deep learning models, especially in the computer vision domain. Currently, common data augmentation techniques are designed manually. Therefore they require…
Data augmentation (DA) has been widely leveraged in computer vision to alleviate data shortage, while its application in medical imaging faces multiple challenges. The prevalent DA approaches in medical image analysis encompass conventional…
Contrary to most machine learning models, modern deep artificial neural networks typically include multiple components that contribute to regularization. Despite the fact that some (explicit) regularization techniques, such as weight decay…
Data augmentation is a powerful technique to improve performance in applications such as image and text classification tasks. Yet, there is little rigorous understanding of why and how various augmentations work. In this work, we consider a…
As more and more artificial intelligence (AI) technologies move from the laboratory to real-world applications, the open-set and robustness challenges brought by data from the real world have received increasing attention. Data augmentation…
Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval, and object detection. Data augmentations are a crucial aspect of pre-training robust…
Mixup is a popular data augmentation technique based on taking convex combinations of pairs of examples and their labels. This simple technique has been shown to substantially improve both the robustness and the generalization of the…
When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm. In…
Data augmentation has become a standard practice in software engineering to address limited or imbalanced data sets, particularly in specialized domains like test classification and bug detection where data can be scarce. Although…
Despite continued advancement in recent years, deep neural networks still rely on large amounts of training data to avoid overfitting. However, labeled training data for real-world applications such as healthcare is limited and difficult to…
Small datasets are common in health research. However, the generalization performance of machine learning models is suboptimal when the training datasets are small. To address this, data augmentation is one solution. Augmentation increases…
Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…
Interdisciplinary research is often at the core of scientific progress. This dissertation explores some advantageous synergies between machine learning, cognitive science and neuroscience. In particular, this thesis focuses on vision and…
Objective: The use of deep learning for electroencephalography (EEG) classification tasks has been rapidly growing in the last years, yet its application has been limited by the relatively small size of EEG datasets. Data augmentation,…
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…
This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data…
Mixup is the latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel level. Inspired by this…
Inspired by the great success of Deep Neural Networks (DNNs) in natural language processing (NLP), DNNs have been increasingly applied in source code analysis and attracted significant attention from the software engineering community. Due…
We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our…