© The Institution of Engineering and Technology
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.
References
-
-
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. 3577–3586.
-
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. 10112–10120.
-
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. 863–872.
-
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. 2974–2983.
-
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. 3002–3011.
-
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. 7428–7435.
-
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. 1912–1920.
-
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. 5017–5032.
-
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)
-
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. 770–779.
-
11)
-
35. Townsend, J.: ‘Differentiating the singular value decomposition’ (, 2016), .
-
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. 12428–12437.
-
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. 3328–3337.
-
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. 1–9.
-
15)
-
20. Gojcic, Z., Zhou, C., Wegner, J.D., et al: .
-
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. 5099–5108.
-
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. Huang, Z., Yu, Y., Xu, J., et al: .
-
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. 4521–4529.
-
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. 356–369.
-
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. 5068–5076.
-
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. 1–6.
-
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. 1–1.
-
24)
-
33. Phong, B.T.: ‘Illumination for computer generated pictures’, Commun. ACM, 1975, 18, (6), pp. 311–317.
-
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)
-
25. Li, Z., Xu, C., Leng, B.: .
-
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. 945–953.
-
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. 2345–2353.
-
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)
-
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. 186–194.
-
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. 9613–9622.
-
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)
-
12. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’, Computer Science, 2014, pp. 1–12, .
-
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. 264–272.
-
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. 1945–1954.
-
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. 7636–7644.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2019.0844
Related content
content/journals/10.1049/iet-ipr.2019.0844
pub_keyword,iet_inspecKeyword,pub_concept
6
6