Design, Analysis and Application of A Volumetric Convolutional Neural Network
This work addresses 3D shape classification for computer vision applications, but it is incremental as it builds on existing volume-based CNN methods.
The authors tackled the problem of 3D shape classification by designing a volumetric convolutional neural network (VCNN) with a systematic method for filter selection and a technique to handle confusing classes, achieving state-of-the-art performance on the ModelNet40 dataset.
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.