Developing Domain-Specific Generative Methods
Name
lewis-kmlewis-phd-eecs-2023-thesis.pdf
Description
Thesis PDF
Size
53.31 MB
Format
Adobe PDF
Checksum (MD5)
fc4b5ac087e285bc3c42f86f918cc94c
Author(s)
Lewis, Kathleen M.
Advisor(s)
Guttag, John V.
Durand, Frédo
Date Issued
September 2023
Publisher
Massachusetts Institute of Technology
Abstract
Generative AI is a field that is rapidly developing and growing in scale. As research in this area shifts to building on large-scale foundation models and powerful architectures, careful thought has to go into adapting these models to new domains and tasks. The work in this thesis demonstrates novel approaches to adapting large-scale generative models and architectures to specific applications in virtual try-on, conceptual art, and domain-specific image classification. In addition to the technical contributions, this thesis explores broader open questions about domain-specific generative models; for example, how can we carefully construct our training data to mitigate bias? What do human-in-the-loop methods for creative generative AI look like in practice? To what extent are large-scale vision-language models useful for traditionally image-only tasks?
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
