Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models.
In experiments, considering three datasets and eight predictive tasks, we find that TaskAug is competitive with or improves on prior work, and the learned policies shed light on what transformations are most effective for different tasks.
Estimating the prevalence of a medical condition, or the proportion of the population in which it occurs, is a fundamental problem in healthcare and public health.
FIDO learns to limit data collection based on an interpretation of data minimization tied to system performance.
In this paper, we present 1) experimental analyses that shed light on cases in which the simple average is suboptimal and 2) a method to address these shortcomings.
Current unsupervised domain adaptation methods can address many types of distribution shift, but they assume data from the source domain is freely available.
Global eradication of malaria depends on the development of drugs effective against the silent, yet obligate liver stage of the disease.
We focus on estimating a patient's risk of cardiovascular death after an acute coronary syndrome based on a patient's raw electrocardiogram (ECG) signal.
We propose an energy-based framework for correcting mislabelled training examples in the context of binary classification.