The vision transformer (ViT) is a state-of-the-art architecture for image recognition tasks that
plays an important role in digital health applications. Medical images account for 90% of the …

Abstract Vision Transformers (ViTs) emerge to achieve impressive performance on many
data-abundant computer vision tasks by capturing long-range dependencies among local …

We investigate a fundamental aspect of machine vision: the measurement of features by
revisiting clustering one of the most classic approaches in machine learning and data …

It is notoriously difficult to train Transformers on small datasets; typically, large pre-trained
models are instead used as the starting point. We explore the weights of such pre-trained …

Training a linear classifier or lightweight model on top of pretrained vision model outputs so-
called'frozen features' leads to impressive performance on a number of downstream few …

Background The approaches based on vision transformers (ViTs) are advancing the field of
medical artificial intelligence (AI) and cancer diagnosis. Recently, many researchers have …

The development of deep learning models in medical image analysis is majorly limited by
the lack of large-sized and well-annotated datasets. Unsupervised learning does not require …

Training a single model on multiple input domains and/or output tasks allows for
compressing information from multiple sources into a unified backbone hence improves …

Weight initialization plays an important role in neural network training. Widely used
initialization methods are proposed and evaluated for networks that are trained from scratch …

Transfer learning has gained significant attention in recent deep learning research due to its
ability to accelerate convergence and enhance performance on new tasks. However, its …