Image Classification with Consistent Supporting Evidence
Name
Wang-wpq-SM-EECS-2022-thesis.pdf
Description
Thesis PDF
Size
5.9 MB
Format
Adobe PDF
Checksum (MD5)
25b52d8e5d46e55be48dd55db2ccf699
Author(s)
Wang, Peiqi(Electrical engineer and computer scientist)
Advisor(s)
Golland, Polina
Date Issued
February 2022
Publisher
Massachusetts Institute of Technology
Abstract
Adoption of machine learning models in healthcare requires end users’ trust in the system. Models that provide additional supportive evidence for their predictions promise to facilitate adoption. We define consistent evidence to be both compatible and sufficient with respect to model predictions. We propose measures of model inconsistency and regularizers that promote more consistent evidence. We demonstrate our ideas in the context of edema severity grading from chest radiographs. We demonstrate empirically that consistent models provide competitive performance while supporting interpretation.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
