Out-of-Distribution Detection for Deep Neural Networks With Isolation Forest and Local Outlier Factor

Out-of-Distribution Detection for Deep Neural Networks With Isolation Forest and Local Outlier Factor

Deep Neural Networks (DNNs) are extensively deployed in today’s safety-critical autonomous systems thanks to their excellent performance. However, they are known to make mistakes unpredictably, e.g., a DNN may misclassify an object if it is used for perception, or issue unsafe control com...

Full description

Bibliographic Details
Main Authors: Siyu Luan, Zonghua Gu, Leonid B. Freidovich, Lili Jiang, Qingling Zhao
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Out-of-distribution
deep neural networks
runtime monitoring
outlier detection
isolation forest
local outlier factor
Online Access:https://ieeexplore.ieee.org/document/9524615/

Internet

https://ieeexplore.ieee.org/document/9524615/

Similar Items