Detecting out-of-distribution (OOD) inputs is a central challenge for safely deploying machine learning models in the real world. Existing solutions are mainly driven by small datasets, with low resolution and very few class labels (e.g., CIFAR). As a result, OOD detection for large-scale image classification tasks remains largely unexplored. In...
[Read More]
Sharon Yixuan Li
Assistant ProfessorDepartment of Computer Sciences
University of Wisconsin-Madison
G. Scholar LinkedIn Github e-Mail