Convolutional Neural Networks (CNNs) have dominated the task of imageclassification since 2012. Some key components of their success are that the
underlying architecture integrates a set inductive biases such as translational
invariance and the training computation can be significantly reduced by employing
weight sharing. CNNs are powerful tools for generating new representations of
images tailored to a particular task such as classification. However, because each
image is passed through the network independent of other images, CNNs are not
able to effectively aggregate information between examples. In this thesis, we
explore the idea of using Graph Neural Networks (GNNs) in conjunction with CNNs
to produce an architecture that has both the representational capacity of a CNN
and the ability to aggregate information between examples.
Graph Neural Networks apply the concept of convolutions directly on graphs. A
result of this is that GNNs are able to learn from the connections between nodes.
However, when working with image datasets, there is no obvious choice on how to
construct a graph. There are certain heuristics such as ensuring homophily that have
empirically been shown to increase the performance of GNNs. In this thesis, we apply
different schemes of constructing a graph from image data for the downstream task of
image classification and experiment with settings such as using multiple feature spaces
and enforcing a bipartite graph structure. We also propose a model that allows for
end to end training using CNNs and GNNs with proxies and attention that improves
classification accuracy in comparison to a regular CNN. / Computer and Information Science
| Identifer | oai:union.ndltd.org:TEMPLE/oai:scholarshare.temple.edu:20.500.12613/6448 |
| Date | January 2021 |
| Creators | Trivedy, Vivek |
| Contributors | Latecki, Longin |
| Publisher | Temple University. Libraries |
| Source Sets | Temple University |
| Language | English |
| Detected Language | English |
| Type | Thesis/Dissertation, Text |
| Format | 56 pages |
| Rights | IN COPYRIGHT- This Rights Statement can be used for an Item that is in copyright. Using this statement implies that the organization making this Item available has determined that the Item is in copyright and either is the rights-holder, has obtained permission from the rights-holder(s) to make their Work(s) available, or makes the Item available under an exception or limitation to copyright (including Fair Use) that entitles it to make the Item available., http://rightsstatements.org/vocab/InC/1.0/ |
| Relation | http://dx.doi.org/10.34944/dspace/6430, Theses and Dissertations |
Page generated in 0.0036 seconds