Concepedia

Concept

out-of-distribution detection

Parents

75

Publications

5.6K

Citations

277

Authors

90

Institutions

About

Out-of-distribution detection is a research area and methodological approach within machine learning focused on identifying input data points that originate from a probability distribution significantly different from the one used to train a given model. This field investigates techniques to distinguish between data drawn from the known training distribution and novel or anomalous data, often assessing model uncertainty or confidence, with the primary significance being the enhancement of system robustness, safety, and reliability in real-world deployment scenarios by preventing potentially erroneous predictions on inputs for which the model is not adequately trained.

Top Authors

Rankings shown are based on concept H-Index.

YL

University of Wisconsin–Madison

YM

University of Wisconsin–Madison

YS

University of Wisconsin–Madison

DH

University of California, Berkeley

SL

University of Illinois Urbana-Champaign

Top Institutions

Rankings shown are based on concept H-Index.

University of Wisconsin–Madison

Madison, United States

Georgia Institute of Technology

Atlanta, United States

Google (United States)

Mountain View, United States

Ridgefield Park, United States

Alexandria, United States