An Approach for Reducing Racial Bias in Facial Monitoring Systems
dc.contributor.author | Ciroski, Viktor | |
dc.contributor.advisor | Azeem Hafeez | |
dc.date.accessioned | 2022-12-15T18:11:55Z | |
dc.date.available | 2022-12-15T18:11:55Z | |
dc.date.issued | 2022-12-17 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/175267 | |
dc.description.abstract | This thesis provides a new approach to reduce racial bias issues and inaccuracies caused by unbalanced benchmark datasets in facial detection systems. It is well known that these unbalanced benchmark datasets significantly over-represent white individuals. It is also understood that a deep learning model performance is based on the data used for training. With these two conjectures, previous research has shown how inaccuracies across different racial groups can be hidden by tracking a single class's labels, faces, and performance. New balanced benchmark datasets have been developed however they lack the variability seen in transitional benchmark sets. Additionally, manually annotating and retraining these models is both computational and financially expensive. Therefore, this research proposed a financially inexpensive way to reduce racial bias within pre-trained facial monitoring systems using semisupervised self-supervised learning. | |
dc.language | English | |
dc.subject | Face detection | |
dc.subject | Deep learning | |
dc.subject | Semi-supervised self-supervised learning | |
dc.subject | S4L | |
dc.subject | Racial bias | |
dc.title | An Approach for Reducing Racial Bias in Facial Monitoring Systems | |
dc.type | Thesis | |
dc.description.thesisdegreename | Master of Science in Engineering (MSE) | en_US |
dc.description.thesisdegreediscipline | Robotics Engineering, College of Engineering & Computer Science | |
dc.description.thesisdegreegrantor | University of Michigan-Dearborn | |
dc.contributor.committeemember | Selim Awad | |
dc.contributor.committeemember | Xuan Zhou | |
dc.subject.hlbtoplevel | Computer Engineering | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/175267/1/Viktor Ciroski Final Thesis.pdf | |
dc.identifier.doi | https://dx.doi.org/10.7302/6648 | |
dc.identifier.orcid | 0000-0001-8855-6158 | |
dc.identifier.name-orcid | Hafeez, Azeem; 0000-0001-8855-6158 | en_US |
dc.working.doi | 10.7302/6648 | en |
dc.owningcollname | Dissertations and Theses (Ph.D. and Master's) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.