The contrastive pre-training of a recognition model on a large dataset of unlabeled data
often boosts the model's performance on downstream tasks like image classification�…

To date, most existing self-supervised learning methods are designed and optimized for
image classification. These pre-trained models can be sub-optimal for dense prediction�…

Self-supervised learning (SSL) methods aim to learn view-invariant representations by
maximizing the similarity between the features extracted from different crops of the same�…

Although deep learning algorithms have achieved significant progress in a variety of
domains, they require costly annotations on huge datasets. Self-supervised learning (SSL)�…

Self-supervised learning algorithms, including BERT and SimCLR, have enabled significant
strides in fields like natural language processing, computer vision, and speech processing�…

Self-supervised learning has been shown to be very effective in learning useful
representations, and yet much of the success is achieved in data types such as images�…

While enabling accelerated acquisition and improved reconstruction accuracy, current deep
MRI reconstruction networks are typically supervised, require fully sampled data, and are�…

Recent self-supervised methods for image representation learning are based on maximizing
the agreement between embedding vectors from different views of the same image. A trivial�…

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision
Transformers (ViT) for natural image analysis. By reconstructing full images from partially�…

In recent years self-supervised learning has emerged as a promising candidate for
unsupervised representation learning. In the visual domain its applications are mostly�…