An Efficient Variational Inference Method for MRF Learning and Structured Prediction Tasks

dc.contributor.advisorRuozzi, Nicholas
dc.contributor.advisorSaquib, Mohammad
dc.contributor.committeeMemberNg, Yu-Chung Vincent
dc.contributor.committeeMemberGogate, Vibhav
dc.contributor.committeeMemberNatarajan, Sriraam
dc.creatorXiong, Hao
dc.date.accessioned2023-02-22T20:59:41Z
dc.date.available2023-02-22T20:59:41Z
dc.date.created2021-12
dc.date.issued2021-12-01T06:00:00.000Z
dc.date.submittedDecember 2021
dc.date.updated2023-02-22T20:59:42Z
dc.description.abstractThe combination of deep neural networks and probabilistic graphical models (PGMs), especially conditional random fields (CRFs), has been studied extensively in recent years, due to a large variety of real world applications that could benefit from combining these two different modeling approaches, especially in the computer vision field, e.g. stereo matching, semantic segmentation and image colorization, etc. However, the traditional methods are either too slow to be applied on large scale PGMs (say grid models over high definition images) or are too simple to yield significant performance improvements. In this dissertation, we propose a highly parallelizeable inference method that is especially suitable for combined CRF + neural network frameworks. We first apply this inference method to general MRF/CRF learning problems, using neural networks to model the potential functions. We show that the resulting model not only yields better classification performance on real-world tasks, but that it also yields a better generative model of the data. We then explain how to combine CRFs with pure deep neural networks, using our inference method as the backbone of the learning process, to solve structured prediction problems in computer vision tasks, e.g. stereo matching, image colorization, semantic segmentation, etc. We show that this strategy is not only efficient on modern GPUs, but it can also achieve superior performance to pure neural network solutions in each problem domain, sometimes dramatically so.
dc.format.mimetypeapplication/pdf
dc.identifier.uri
dc.identifier.urihttps://hdl.handle.net/10735.1/9612
dc.language.isoen
dc.subjectComputer Science
dc.subjectArtificial Intelligence
dc.subjectStatistics
dc.titleAn Efficient Variational Inference Method for MRF Learning and Structured Prediction Tasks
dc.typeThesis
dc.type.materialtext
thesis.degree.collegeSchool of Engineering and Computer Science
thesis.degree.departmentComputer Science
thesis.degree.grantorThe University of Texas at Dallas
thesis.degree.namePHD

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
XIONG-PRIMARY-2022-1.pdf
Size:
3.69 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.84 KB
Format:
Plain Text
Description: