國立虎尾科技大學 |

H3DNET : = A Deep Learning Framework for Hierarchical 3D Object Classification.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	H3DNET :/
其他題名:	A Deep Learning Framework for Hierarchical 3D Object Classification.
作者:	Patel, Marmikkumar.
面頁冊數:	1 online resource (97 pages)
附註:	Source: Masters Abstracts International, Volume: 57-04.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9780355615777

H3DNET : = A Deep Learning Framework for Hierarchical 3D Object Classification.
Patel, Marmikkumar.

H3DNET :A Deep Learning Framework for Hierarchical 3D Object Classification. - 1 online resource (97 pages)

Source: Masters Abstracts International, Volume: 57-04.

Thesis (M.S.)--University of Missouri - Kansas City, 2017.

Includes bibliographical references

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.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355615777Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

H3DNET : = A Deep Learning Framework for Hierarchical 3D Object Classification.
LDR:03080ntm a2200361K 4500 001 912198
005 20180608102941.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355615777
035 $a (MiAaPQ)AAI10743336
035 $a (MiAaPQ)umkc:11232
035 $a AAI10743336
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Patel, Marmikkumar. $3 1184448
245 1 0 $a H3DNET : $b A Deep Learning Framework for Hierarchical 3D Object Classification.
264 0 $c 2017
300 $a 1 online resource (97 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 57-04.
500 $a Adviser: Yugyung Lee.
502 $a Thesis (M.S.)--University of Missouri - Kansas City, 2017.
504 $a Includes bibliographical references
520 $a 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.
520 $a 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 the 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.
520 $a The H3DNET framework was implemented in TensorFlow which is capable of using GPU computations in parallel to build the 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 and POINTNET.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Artificial intelligence. $3 559380
650 4 $a Library science. $3 561163
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0800
690 $a 0399
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Missouri - Kansas City. $b Computer Science. $3 1182463
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10743336 $z click for full text (PQDT)