access icon free Balanced principal component for 3D shape recognition using convolutional neural networks

Currently, PCA (principal component analysis) is widely used in many neural networks and has become a crucial part of the convolutional neural network (CNN) feature extraction. However, whether PCA is suitable for this process remains to be elucidated. The authors proposed a new method called balanced principal component (BPC) that generates a balanced local feature and combines with CNN as a layer to cope with the fusion problem. Specifically, BPC layer includes regionalisation module and average compression PCA (AC-PCA) module. First, they used regionalisation module to generate some sub-region that focuses on the local feature in each view. Secondly, the AC-PCA module is a computational process that enlarges the feature matrix by PCA and eventually compacts the matrix to a one-dimensional (1D) vector by AC. Next, all 1D vectors are compacted by AC to obtain a multi-dimensional balance. Finally, they designed this layer with an end-to-end trainable structure to promote the feature extraction task of CNN. They addressed 3D shapes using a projection method that is pre-trained on ImageNet and migration learning on ModelNet dataset. By comparing with the state-of-the-art network, they achieved a significant gain in performance of retrieval and classification tasks.

Inspec keywords: image representation; image classification; neural nets; principal component analysis; shape recognition; learning (artificial intelligence); image recognition; feature extraction

Other keywords: state-of-the-art network; BPC layer; regionalisation module; CNN; 3D shape recognition; principal component analysis; balanced local feature; balanced principal component; AC-PCA module; convolutional neural network; neural networks; computational process; projection method; multidimensional balance; feature matrix; feature extraction task; average compression PCA module; one-dimensional vector

Subjects: Knowledge engineering techniques; Other topics in statistics; Other topics in statistics; Computer vision and image processing techniques; Image recognition; Neural computing techniques

References

    1. 1)
      • 23. Riegler, G., Osman-Ulusoy, A., Geiger, A.: ‘Octnet: learning deep 3D representations at high resolutions’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017, pp. 35773586.
    2. 2)
      • 1. Ben-Shabat, Y., Lindenbaum, M., Fischer, A.: ‘Nesti-net: normal estimation for unstructured 3D point clouds using convolutional neural networks’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 2019, pp. 1011210120.
    3. 3)
      • 21. Klokov, R., Lempitsky, V.: ‘Escape from cells: deep kd-networks for the recognition of 3D point cloud models’. Proc. of the IEEE Int. Conf. on Computer Vision, Honolulu, HI, USA, 2017, pp. 863872.
    4. 4)
      • 31. Sun, X., Wu, J., Zhang, X., et al: ‘Pix3d: dataset and methods for single-image 3D shape modeling’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 29742983.
    5. 5)
      • 26. Chu, H., Ma, W.C., Kundu, K., et al: ‘Surfconv: bridging 3D and 2D convolution for rgbd images’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 30023011.
    6. 6)
      • 29. Xu, C., Leng, B., Zhang, C., et al: ‘Emphasizing 3D properties in recurrent multi-view aggregation for 3D shape retrieval’. Proc. of the Thirty-Second AAAI Conf. on Artificial Intelligence, New Orleans, LA, USA, 2018, pp. 74287435.
    7. 7)
      • 22. Wu, Z., Song, S., Khosla, A., et al: ‘3D shapenets: a deep representation for volumetric shapes’. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 2015, pp. 19121920.
    8. 8)
      • 14. Chan, T.H., Jia, K., Gao, S., et al: ‘Pcanet: a simple deep learning baseline for image classification?’, IEEE Trans. Image Process., 2015, 24, (12), pp. 50175032.
    9. 9)
      • 16. Kim, A., Song, J., Gwun, O., et al: ‘3D model retrieval using convex hull and curvature’. Proceedings of the 2008 International Conference on Computer Graphics Virtual Reality, CGVR, Las Vegas, NV, USA, 2008.
    10. 10)
      • 19. Shi, S., Wang, X., Li, H.: ‘Pointrcnn: 3D object proposal generation and detection from point cloud’. 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 2018, pp. 770779.
    11. 11)
      • 35. Townsend, J.: ‘Differentiating the singular value decomposition’ (Technical Report, 2016), https://j-towns.github.io/papers/svd-derivative.pdf.
    12. 12)
      • 2. Zhang, W., Xiao, C.: ‘Pcan: 3D attention map learning using contextual information for point cloud based retrieval’. 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, pp. 1242812437.
    13. 13)
      • 7. Xu, L., Sun, H., Liu, Y.: ‘Learning with batch-wise optimal transport loss for 3D shape recognition’. 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, pp. 33283337.
    14. 14)
      • 13. Szegedy, C., Liu, W., Jia, Y., et al: ‘Going deeper with convolutions’. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 19.
    15. 15)
      • 20. Gojcic, Z., Zhou, C., Wegner, J.D., et al: ‘Learning multiview 3D point cloud registration’. ArXiv, 2020, abs/2001.05119.
    16. 16)
      • 24. Qi, C.R., Yi, L., Su, H., et al: ‘Pointnet++: deep hierarchical feature learning on point sets in a metric space’. Advances in Neural Information Processing Systems, Long Beach, CA, USA, 2017, pp. 50995108.
    17. 17)
      • 15. Xin, L.: ‘The shape feature extraction and retrieval of three dimensional CAD models’ (University of Science and Technology of China, China, 2017).
    18. 18)
      • 18. Huang, Z., Yu, Y., Xu, J., et al: ‘Pf-net: Point fractal network for 3D point cloud completion’. ArXiv, 2020, abs/2003.00410.
    19. 19)
      • 27. Niu, C., Li, J., Xu, K.: ‘Im2struct: recovering 3D shape structure from a single rgb image’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 45214529.
    20. 20)
      • 17. Tombari, F., Salti, S., Di-Stefano, L.: ‘Unique signatures of histograms for local surface description’. European Conf. on Computer Vision, Heraklion, Crete, Greece, 2010, pp. 356369.
    21. 21)
      • 6. Xie, J., Dai, G., Zhu, F., et al: ‘Learning barycentric representations of 3D shapes for sketch-based 3D shape retrieval’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017, pp. 50685076.
    22. 22)
      • 3. Kuang, Z., Yu, J., Fan, J., et al: ‘Deep point convolutional approach for 3D model retrieval’. 2018 IEEE International Conference on Multimedia and Expo (ICME), San Diego, CA, USA, 2018, pp. 16.
    23. 23)
      • 10. Yu-Ting, S., Li, W.H., Nie, W., et al: ‘Unsupervised feature learning with graph embedding for view-based 3D model retrieval’, IEEE Access, 2019, PP, pp. 11.
    24. 24)
      • 33. Phong, B.T.: ‘Illumination for computer generated pictures’, Commun. ACM, 1975, 18, (6), pp. 311317.
    25. 25)
      • 36. Szegedy, C., Ioffe, S., Vanhoucke, V., et al: ‘Inception-v4, inception-resnet and the impact of residual connections on learning’. Thirty-First AAAI Conf. on Artificial Intelligence, San Francisco, CA, USA, 2017.
    26. 26)
      • 25. Li, Z., Xu, C., Leng, B.: ‘Angular triplet-center loss for multi-view 3D shape retrieval’, ArXiv, 2019, abs/1811.08622.
    27. 27)
      • 5. Su, H., Maji, S., Kalogerakis, E., et al: ‘Multi-view convolutional neural networks for 3D shape recognition’. Proc. of the IEEE Int. Conf. on Computer Vision, Santiago, Chile, 2015, pp. 945953.
    28. 28)
      • 32. Xu, B., Chen, Z.: ‘Multi-level fusion based 3D object detection from monocular images’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 23452353.
    29. 29)
      • 11. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘Imagenet classification with deep convolutional neural networks’. Int. Conf. on Neural Information Processing Systems, Lake Tahoe, NV, USA, 2012.
    30. 30)
      • 8. Yu, T., Meng, J., Yuan, J.: ‘Multi-view harmonized bilinear network for 3D object recognition’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 186194.
    31. 31)
      • 34. Wu, W., Qi, Z., Li, F.: ‘Pointconv: deep convolutional networks on 3D point clouds’. 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 2018, pp. 96139622.
    32. 32)
      • 4. Le, H.M., Do, T.T., Hoang, T., et al: ‘Sdrsac: semidefinite-based randomized approach for robust point cloud registration without correspondences’. The IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019.
    33. 33)
      • 12. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’, Computer Science, 2014, pp. 112, arXiv:1409.1556.
    34. 34)
      • 9. Feng, Y., Zhang, Z., Zhao, X., et al: ‘Gvcnn: group-view convolutional neural networks for 3D shape recognition’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 264272.
    35. 35)
      • 30. He, X., Zhou, Y., Zhou, Z., et al: ‘Triplet-center loss for multi-view 3D object retrieval’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 19451954.
    36. 36)
      • 28. Li, P., Chen, X., Shen, S.: ‘Stereo R-CNN based 3D object detection for autonomous driving’. 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, pp. 76367644.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2019.0844
Loading

Related content

content/journals/10.1049/iet-ipr.2019.0844
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading