2026-09-18T19:04:42Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1515322023-08-01T04:24:15Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Ghassemi, Marzyeh
Hulkund, Neha
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2023-07-31T19:46:46Z
2023-07-31T19:46:46Z
2023-06
2023-06-06T16:35:04.864Z
https://hdl.handle.net/1721.1/151532
Out-of-distribution (OOD) detection is an important part of enabling the real world deployment of machine learning models. Many recent methods developed to perform OOD detection rely on calculating a score function on a given test point then thresholding the value to classify the point as in-distribution (ID) or OOD. However, calculating a score function on a single example may give biased or inaccurate estimates, especially as examples are sampled further and further OOD. In this paper we propose TraM: Transformation Neighborhood Marginalization, a method to improve the estimation of score functions used for OOD detection by calculating their expectation over a transformation neighborhood. TraM demonstrates improvements on a subset of commonly used OOD score functions in the OpenOOD benchmark, improving a baseline ODIN score function by up to 6 AUROC. However, it is not found to improve other baseline metrics signficantly, indicating the need for further research on this topic.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Neighborhood Transformation Marginalization forOOD Detection
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="0658f9e1-613f-450b-8628-ce9cff0a0cf3">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Neighborhood Transformation Marginalization forOOD Detection</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2023-06</PublicationDate>
<Authors>
<Author>
<DisplayName>Hulkund, Neha</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Out-of-distribution (OOD) detection is an important part of enabling the real world deployment of machine learning models. Many recent methods developed to perform OOD detection rely on calculating a score function on a given test point then thresholding the value to classify the point as in-distribution (ID) or OOD. However, calculating a score function on a single example may give biased or inaccurate estimates, especially as examples are sampled further and further OOD. In this paper we propose TraM: Transformation Neighborhood Marginalization, a method to improve the estimation of score functions used for OOD detection by calculating their expectation over a transformation neighborhood. TraM demonstrates improvements on a subset of commonly used OOD score functions in the OpenOOD benchmark, improving a baseline ODIN score function by up to 6 AUROC. However, it is not found to improve other baseline metrics signficantly, indicating the need for further research on this topic.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>