Deformable convolutional networks for multi-view 3D shape classification

Deformable convolutional networks for multi-view 3D shape classification

For access to this article, please select a purchase option:

Buy article PDF
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
Electronics Letters — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

This Letter suggests a novel method for improving the robustness and the geometric transformation modelling capability in multi-view convolutional networks (MVCNNs). First, the deformable convolutional networks are used to learn more details and features related to the geometric transformation which the standard convolutional neural networks cannot handle. Then a view-pooling layer is specifically designed for combining the descriptors from multiple views as the final representations of the 3D shapes. The key idea is to insert the deformable convolutional layer between the input and convolutional layer, making it possible to solve deformable 3D shape classification problems, which was a challenging task for MVCNN framework. The proposed method achieves state-of-the-art classification results on two subsets of the ModelNet dataset (ModelNet10 and ModelNet40) over previous methods by a significant margin.


    1. 1)
      • 1. Dai, J., Qi, H., Xiong, Y., et al: ‘Deformable convolutional networks’. IEEE Int. Conf. Computer Vision (ICCV), Venice, Italy, October 2017, pp. 764773.
    2. 2)
      • 2. Su, H., Maji, S., Kalogerakis, E., et al: ‘Multi-view convolutional neural networks for 3D shape recognition’. IEEE Int. Conf. Computer Vision (ICCV), Santiago, Chile, December 2015, pp. 945953.
    3. 3)
    4. 4)
    5. 5)
      • 5. Wu, Z., Song, S., Khosla, A., et al: ‘3D shapeNets: a deep representation for volumetric shapes’. The IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, June 2015, pp. 19121920.
    6. 6)
      • 6. Xu, X., Corrigan, D., Dehghani, A., et al: ‘3D object recognition based on volumetric representation using convolutional neural networks’. Int. Conf. on Articulated Motion and Deformable Objects, Palma de Mallorca, Spain, June 2016, pp. 147156.
    7. 7)
      • 7. Qi, C.R., Su, H., Niessner, M., et al: ‘Volumetric and multi-view CNNs for object classification on 3D data’. The IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, June 2016, pp. 56485656.
    8. 8)
    9. 9)
      • 9. Kalogerakis, E., Averkiou, M., Maji, S., et al: ‘3D shape segmentation with projective convolutional networks’. The IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, July 2017, pp. 66306639.
    10. 10)
    11. 11)
      • 11. Dai, J., Li, Y., He, K., et al: ‘R-fcn: object detection via region-based fully convolutional networks’. Neural Information Processing Systems (NIPS), Barcelona, Spain, December 2016.
    12. 12)
      • 12. Jaderberg, M., Simonyan, K., Zisserman, A., et al: ‘Spatial transformer networks’. Neural Information Processing Systems (NIPS), Montreal, Canada, December 2015, pp. 19.
    13. 13)
      • 13. Johns, E., Leutenegger, S., Davison, A.J.: ‘Pairwise decomposition of image sequences for active multi-view recognition’. The IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, June 2016, pp. 38133822.
    14. 14)
      • 14. Chatfield, K., Simonyan, K., Vedaldi, A., et al: ‘Return of the devil in the details: delving deep into convolutional nets’. British Machine Vision Conf. (BMVC), Nottingham, UK, September 2014.
    15. 15)
      • 15. Srivastava, N., Hinton, G.E., Krizhevsky, A., et al: ‘Dropout: a simple way to prevent neural networks from overfitting’, Journal of Machine Learning Research, 2014, 15, (1), pp. 19291958.

Related content

This article has following corresponding article(s):
in brief
This is a required field
Please enter a valid email address