A Simple Framework for Robust Out-of-Distribution Detection

A Simple Framework for Robust Out-of-Distribution Detection

Out-of-distribution (OOD) detection, i.e., identifying whether a given test sample is drawn from outside the training distribution, is essential for a deep classifier to be deployed in a real-world application. The existing state-of-the-art methods of OOD detection tackle this issue by utilizing the...

Full description

Bibliographic Details
Main Authors: Youngbum Hur, Eunho Yang, Sung Ju Hwang
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Out-of-distribution detection
network calibration
deep neural networks
consistency regularization
self-supervised learning
Online Access:https://ieeexplore.ieee.org/document/9718325/

Internet

https://ieeexplore.ieee.org/document/9718325/

Similar Items