Carcinomas are complex ecosystems composed of cancer, stromal and immune cells.
Communication between these cells and their microenvironments induces cancer …

Learning from positive and unlabeled data or PU learning is the setting where a learner only
has access to positive examples and unlabeled data. The assumption is that the unlabeled …

Positive-Unlabeled (PU) learning tries to learn binary classifiers from a few labeled positive
examples with many unlabeled ones. Compared with ordinary semi-supervised learning …

Self-training and contrastive learning have emerged as leading techniques for incorporating
unlabeled data, both under distribution shift (unsupervised domain adaptation) and when it …

Despite the emergence of principled methods for domain adaptation under label shift, their
sensitivity to shifts in class conditional distributions is precariously under explored …

We introduce the problem of domain adaptation under Open Set Label Shift (OSLS), where
the label distribution can change arbitrarily and a new class may arrive during deployment …

Using unlabeled data to regularize the machine learning models has demonstrated promise
for improving safety and reliability in detecting out-of-distribution (OOD) data. Harnessing the …

Positive-Unlabeled (PU) data arise frequently in a wide range of fields such as medical
diagnosis, anomaly analysis and personalized advertising. The absence of any known …

Learning binary classifiers from positive and unlabeled data (PUL) is vital in many real-world
applications, especially when verifying negative examples is difficult. Despite the impressive …

Cardiac segmentation is an essential step for the diagnosis of cardiovascular diseases.
However, pixel-wise dense labeling is both costly and time-consuming. Scribble, as a form …