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

## TL;DR

This paper introduces a systematically designed volumetric CNN with a novel filter determination method, analyzes its causes of classification confusion, and demonstrates its superior performance on 3D shape classification tasks.

## Contribution

It proposes a feed-forward K-means clustering algorithm for filter design and a hierarchical clustering with random forest for improved classification among confusing classes.

## Key findings

- Achieves state-of-the-art results on ModelNet40 dataset.
- Provides a systematic design approach for volumetric CNNs.
- Analyzes the relationship between filter weights and classification confusion.

## 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.