Neural networks are prone to overfitting and memorizing data patterns. To avoid over-fitting
and enhance their generalization and performance, various methods have been suggested …

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 …

Federated learning shows a bright promise as a privacy-preserving collaborative learning
technique. However, prevalent solutions mainly focus on all private data sampled from the …

Modern data augmentation using a mixture-based technique can regularize the models from
overfitting to the training data in various computer vision applications, but a proper data …

Unsupervised clustering aims at discovering the semantic categories of data according to
some distance measured in the representation space. However, different categories often …

Recently, contrastive learning-based image translation methods have been proposed, which
contrasts different spatial locations to enhance the spatial correspondence. However, the …

In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good
representations by encouraging them to be invariant under meaningful transformations …

Inspired by the recent progress in self-supervised learning for computer vision that
generates supervision using data augmentations, we explore a new general-purpose audio …

We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored
topic despite the wide adoption of the ViT architectures to different tasks. To tackle this …

Contrastive learning models based on Siamese structure have demonstrated remarkable
performance in self-supervised learning. Such a success of contrastive learning relies on …