Learning-Based Multiple Pooling Fusion in Multi-View Convolutional Neural Network for 3D Model Classification and Retrieval

Hui Zeng, Qi Wang, Chen Li and Wei Song
Volume: 15, No: 5, Page: 1179 ~ 1191, Year: 2019
10.3745/JIPS.02.0120
Keywords: Learning-Based Multiple Pooling Fusion, Multi-View Convolutional Neural Network, 3D Model Classification, 3D Model Retrieval
Full Text:

Abstract
We design an ingenious view-pooling method named learning-based multiple pooling fusion (LMPF), and apply it to multi-view convolutional neural network (MVCNN) for 3D model classification or retrieval. By this means, multi-view feature maps projected from a 3D model can be compiled as a simple and effective feature descriptor. The LMPF method fuses the max pooling method and the mean pooling method by learning a set of optimal weights. Compared with the hand-crafted approaches such as max pooling and mean pooling, the LMPF method can decrease the information loss effectively because of its “learning” ability. Experiments on ModelNet40 dataset and McGill dataset are presented and the results verify that LMPF can outperform those previous methods to a great extent.

Article Statistics
Multiple requests among the same broswer session are counted as one view (or download).
If you mouse over a chart, a box will show the data point's value.


Cite this article
IEEE Style
H. Zeng, Q. Wang, C. Li and W. Song, "Learning-Based Multiple Pooling Fusion in Multi-View Convolutional Neural Network for 3D Model Classification and Retrieval," Journal of Information Processing Systems, vol. 15, no. 5, pp. 1179~1191, 2019. DOI: 10.3745/JIPS.02.0120.

ACM Style
Hui Zeng, Qi Wang, Chen Li, and Wei Song. 2019. Learning-Based Multiple Pooling Fusion in Multi-View Convolutional Neural Network for 3D Model Classification and Retrieval, Journal of Information Processing Systems, 15, 5, (2019), 1179~1191. DOI: 10.3745/JIPS.02.0120.