Data augmentation (DA) is indispensable in modern machine learning and deep neural
networks. The basic idea of DA is to construct new training data to improve the model's …

Fine-tuning pretrained language models (LMs) without making any architectural changes
has become a norm for learning various language downstream tasks. However, for non …

We propose the first unified theoretical analysis of mixed sample data augmentation
(MSDA), such as Mixup and CutMix. Our theoretical results show that regardless of the …

Abstract Knowledge distillation (KD) is a general neural network training approach that uses
a teacher model to guide the student model. Existing works mainly study KD from the …

Mixup, which creates synthetic training instances by linearly interpolating random sample
pairs, is a simple and yet effective regularization technique to boost the performance of deep …

A large number of newly built infrastructures as well as those constructed in the early stage
are faced with the problems of detection and maintenance. However, it is difficult to detect …

As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data
augmentations have garnered increasing attention as regularization techniques when …

Abstract Graph Neural Networks (GNNs) have shown great performance in various tasks,
with the core idea of learning from data labels and aggregating messages within the …

Mixup is a powerful data augmentation strategy that has been shown to improve the
generalization and adversarial robustness of machine learning classifiers, particularly in …

Long-tailed image recognition is a computer vision problem considering a real-world class
distribution rather than an artificial uniform. Existing methods typically detour the problem by …