Towards regression-free and source-free online domain adaptation

Simple item page
dc.contributor.authorMusabe, Taif Al
dc.contributor.examiningcommitteeLeung, Carson (Computer Science)
dc.contributor.examiningcommitteeMohammed, Noman (Computer Science)
dc.contributor.supervisorWang, Yang
dc.contributor.supervisorWang, Shaowei
dc.date.accessioned2024-03-25T19:15:18Z
dc.date.available2024-03-25T19:15:18Z
dc.date.issued2024-03-13
dc.date.submitted2024-03-25T16:22:44Zen_US
dc.degree.disciplineComputer Scienceen_US
dc.degree.levelMaster of Science (M.Sc.)
dc.description.abstractIn real-world applications, inconsistent behavior displayed by AI models before and after updates can have severe consequences, particularly in safety-critical systems like autonomous driving. The updated model may exhibit regression issues, leading to incorrect predictions that were previously accurate. While regression problems have been extensively studied in various contexts, their investigation within the realm of online domain adaptation remains limited. This poses a unique challenge due to the continuous updating of the old model with incoming data streams, potentially worsening regression problems in the source domain. In this work, we address the regression problem in online domain adaptation by mitigating regression rates in the source data while adapting to a streaming target data. Our proposed approach introduces a novel loss incorporated into the Crodobo framework. This ensures that the new model learns from the source domain in a supportive manner, avoiding the acquisition of irrelevant information and preserving privacy by removing data after successful domain adaptation. While the Crodobo framework relies on raw source data, which may contain sensitive information. Hence, it does not guarantee overall privacy protection. Consequently, we also address the privacy concerns by replacing direct access to raw data with synthetic data. Through a generative model, we force the use of synthetic data, transforming online domain adaptation into a source-free process. This guarantees the confidentiality of source data, minimizes storage requirements, and enhances the practicality of the system. Our methodologies undergoe extensive evaluation on datasets such as Visda-C, COVID-DA, and MNIST - USPS. The experimental results validate the effectiveness of our approaches.
dc.description.noteMay 2024
dc.identifier.urihttp://hdl.handle.net/1993/38078
dc.language.isoeng
dc.rightsopen accessen_US
dc.subjectSource-Free Domain Adaption
dc.subjectOnline Domain Adaption
dc.subjectDomain Adaption
dc.subjectRegression Problem
dc.titleTowards regression-free and source-free online domain adaptation
dc.typemaster thesisen_US
local.subject.manitobano
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Towards Regression-Free And Source-Free Online Domain Adaptation.pdf
Size:
8.35 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
770 B
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
FGS - Electronic Theses and Practica