Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks

Apoorva Sharma; Navid Azizan; Marco Pavone

Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks

Apoorva Sharma, Navid Azizan, Marco Pavone

Research output: Contribution to conference › Paper › peer-review

Original language	English
Pages	1958-1967
Number of pages	10
Publication status	Published - 2021
Externally published	Yes
Event	37th Conference on Uncertainty in Artificial Intelligence, UAI 2021 - Virtual, Online Duration: Jul 27 2021 → Jul 30 2021

Conference

Conference	37th Conference on Uncertainty in Artificial Intelligence, UAI 2021
City	Virtual, Online
Period	7/27/21 → 7/30/21

ASJC Scopus Subject Areas

Artificial Intelligence
Applied Mathematics

Cite this

@conference{6a369266a0a34a55adcdcfa90ce95938,

title = "Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks",

author = "Apoorva Sharma and Navid Azizan and Marco Pavone",

note = "Publisher Copyright: {\textcopyright} 2021 37th Conference on Uncertainty in Artificial Intelligence, UAI 2021. All Rights Reserved.; 37th Conference on Uncertainty in Artificial Intelligence, UAI 2021 ; Conference date: 27-07-2021 Through 30-07-2021",

year = "2021",

language = "English",

pages = "1958--1967",

}

TY - CONF

T1 - Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks

AU - Sharma, Apoorva

AU - Azizan, Navid

AU - Pavone, Marco

PY - 2021

Y1 - 2021

UR - http://www.scopus.com/inward/record.url?scp=85115853197&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85115853197&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85115853197

SP - 1958

EP - 1967

T2 - 37th Conference on Uncertainty in Artificial Intelligence, UAI 2021

Y2 - 27 July 2021 through 30 July 2021

ER -

Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks

Conference

ASJC Scopus Subject Areas

Other files and links

Fingerprint

Cite this