dc.contributor.advisor | Lee, Yugyung, 1960- | |
dc.contributor.author | Patel, Marmikkumar | |
dc.date.issued | 2017 | |
dc.date.submitted | 2017 Fall | |
dc.description | Title from PDF of title page viewed January 31, 2018 | |
dc.description | Thesis advisor: Yugyung Lee | |
dc.description | Vita | |
dc.description | Includes bibliographical references (pages 81-83) | |
dc.description | Thesis (M.S.)--School of Computing and Engineering. University of Missouri--Kansas City, 2017 | |
dc.description.abstract | Deep learning has received a lot of attention in the fields such as speech recognition and
image classification because of the ability to learn multiple levels of features from raw data.
However, 3D deep learning is relatively new but in high demand with their great research values.
Current research and usage of deep learning for 3D data suffer from the limited ability to process
large volumes of data as well as low performance, especially in increasing the number of classes
in the image classification task. One of the open questions is whether an efficient as well as an
accurate 3D Deep Learning model can be built with large-scale 3D data.
In this thesis, we aim to design a hierarchical framework for 3D Deep Learning, called
H3DNET, which can build a DL 3D model in a distributed and scalable manner. In the H3DNET
framework, a learning problem is composed of two stages: divide and conquer. At the divide
learning stage, a learning problem is divided into several smaller problems. At the conquer
learning stage, an optimized solution is used to solve these smaller subproblems for a better
learning performance. This involves training of models and optimizing them with refined division
for a better performance. The inferencing can achieve the efficiency and high accuracy with fuzzy
classification using such a two-step approach in a hierarchical manner.
The H3DNET framework was implemented in TensorFlow which is capable of using GPU
computations in parallel to build 3D neural network. We evaluated the H3DNET framework on a
3D object classification with MODELNET10 and MODELNET40 datasets to check the efficiency of
the framework. The evaluation results verified that the H3DNET framework supports hierarchical
3D Deep Learning with 3D images in a scalable manner. The classification accuracy is higher than
the state-of-the-art, VOXNET[7] and POINTNET. | eng |
dc.description.tableofcontents | Introduction -- Background and related work -- The hierarchical 3D net of 3D object classification -- Results and evaluation -- Conclusion and future work | |
dc.format.extent | xiii, 84 pages | |
dc.identifier.uri | https://hdl.handle.net/10355/62669 | |
dc.publisher | University of Missouri--Kansas City | eng |
dc.subject.lcsh | Machine learning | |
dc.subject.lcsh | Three-dimensional display systems | |
dc.subject.other | Thesis -- University of Missouri--Kansas City -- Computer science | |
dc.title | H3DNET: A Deep Learning Framework for Hierarchical 3D Object Classification | eng |
dc.type | Thesis | eng |
thesis.degree.discipline | Computer Science (UMKC) | |
thesis.degree.grantor | University of Missouri--Kansas City | |
thesis.degree.level | Masters | |
thesis.degree.name | M.S. | |