Despite increasing numbers of regulatory approvals, deep learning-based computational
pathology systems often overlook the impact of demographic factors on performance …

The sample selection approach is popular in learning with noisy labels. The state-of-the-art
methods train two deep networks simultaneously for sample selection, which aims to employ …

Abstract Domain generalization aims to learn from multiple source domains a predictive
model that can generalize to unseen target domains. One essential problem in domain …

Human-annotated labels are often prone to noise, and the presence of such noise will
degrade the performance of the resulting deep neural network (DNN) models. Much of the …

Despite the remarkable performance that modern deep neural networks have achieved on
independent and identically distributed (IID) data, they can crash under distribution shifts …

Background In recent years, ophthalmology has emerged as a new frontier in medical
artificial intelligence (AI) with multi-modal AI in ophthalmology garnering significant attention …

In the past decade, the deployment of deep learning (Artificial Intelligence (AI)) methods has
become pervasive across a spectrum of real-world applications, often in safety-critical …

Organizations rely on machine learning engineers (MLEs) to operationalize ML, ie, deploy
and maintain ML pipelines in production. The process of operationalizing ML, or MLOps …

Leveraging weak or noisy supervision for building effective machine learning models has
long been an important research problem. Its importance has further increased recently due …

The presence of label noise often misleads the training of deep neural networks. Departing
from the recent literature which largely assumes the label noise rate is only determined by …