Design, Analysis and Application of A Volumetric Convolutional Neural Network release_dibzzyqwgvdfnh6kado3zxq7b4

by Xiaqing Pan, Yueru Chen, C.-C. Jay Kuo

Released as a article .

2017  

Abstract

The design, analysis and application of a volumetric convolutional neural network (VCNN) are studied in this work. Although many CNNs have been proposed in the literature, their design is empirical. In the design of the VCNN, we propose a feed-forward K-means clustering algorithm to determine the filter number and size at each convolutional layer systematically. For the analysis of the VCNN, the cause of confusing classes in the output of the VCNN is explained by analyzing the relationship between the filter weights (also known as anchor vectors) from the last fully-connected layer to the output. Furthermore, a hierarchical clustering method followed by a random forest classification method is proposed to boost the classification performance among confusing classes. For the application of the VCNN, we examine the 3D shape classification problem and conduct experiments on a popular ModelNet40 dataset. The proposed VCNN offers the state-of-the-art performance among all volume-based CNN methods.
In text/plain format

Archived Files and Locations

application/pdf  6.1 MB
file_zefjnl44lbdtdk4lg5kqbvxexi
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2017-02-01
Version   v1
Language   en ?
arXiv  1702.00158v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 074b50ba-f3cc-4e0b-b6a9-8e9cced2509b
API URL: JSON