Abstract
Traditional convolutional neural networks (CNNs) are limited to be directly applied to 3D graph data due to their inherent grid structure. And most of graph-based learning methods use local-to-global hierarchical structure learning, and often ignore the global context. To overcome these issues, we propose two strategies: one is topological learning with 3D offset convolution, which provides learnable parameters in local graph construction, effectively expands the sampling space and improves the perception ability of diverse local structures. The other is geometrical learning with an adaptive spec-graph convolution network (AsGCN), which establishes a joint learning mechanism of local geometry in spatial domain and global structure in feature domain, and generates informative deep features through spectral filtering and weighting. Extensive experiments demonstrate that our deep features have strong discerning ability and robustness to non-rigid transformed graph data, incomplete mesh data, and better performance can be obtained compared to state-of-the-art methods.
Similar content being viewed by others
Data Availability
The datasets generated and/or analysed during the current study are available in the GCN repository at https://github.com/zizigbjuan/GCN
Some models, or code generated or used during the study are available from the corresponding author by request.
References
Bansal M, Kumar M, Sachdeva M, Mittal A (2021) Transfer learning for image classification using VGG19: Caltech-101 image data set. J Ambient Intell Humaniz Comput:1–12
Berwin A (1993) Bandwidth selection in kernel density estimation: a review. In CORE and Institut de Statistique Citeseer
Bronstein A, Bronstein M, Guibas L, Ovsjanikov M (2011) Shape Google: geometric words and expressions for invariant shape retrieval. ACM Trans Graph 30(1):1–22
Bruna J, Zaremba W, Szlam A, LeCun Y (2013) Spectral networks and locally connected networks on graphs. Computer Science
Cangea C, Veličković P, Jovanović N, Kipf T, Liò P (2018) Towards sparse hierarchical graph classifiers. arXiv preprint arXiv:1811.01287
Chen J, Ma T, Xiao C (2018) Fastgcn: fast learning with graph convolutional networks via importance sampling. In Proc. International Conference on Learning Representations (ICLR)
Chhabra P, Garg NK (2020) M K umar. Content-based image retrieval system using ORB and SIFT features. Neural Comput & Applic 32(7):1–9
Chiang W, Liu X, Si S, Li Y, Bengio S, Hsieh C (2019) Cluster-gcn: an efficient algorithm for training deep and large graph convolutional networks. In: Proc. of KDD. ACM
Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in Neural Information Processing Systems, 3844–3852
Gilmer J, Schoenholz S, Riley P, Vinyals O, Dahl G (2017) Neural message passing for quantum chemistry. In Proc. 34th international conference on machine learning, PMLR. Sydney, Australia: 1263–1272
Hamilton W, Ying R, Leskovec J (2017) Inductive representation learning on large graphs. In NIPS
Hammond D, Vandergheynst P, Gribonval R (2011) Wavelets on graphs via spectral graph theory. Appl Comput Harmon Anal 30(2):129–150
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In CVPR, USA: 770–778
Hermosilla P, Ritschel T, Vazquez P, Vinacua A, Ropinski T (2018) Monte carlo convolution for learning on non-uniformly sampled point clouds. In SIGGRAPH Asia 2018 Technical Papers, page 235. ACM
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proc. of International Conference on Learning Representations (ICLR)
Klokov R, Lempitsky V (2017) Escape from Cells: deep Kd-Networks for the recognition of 3d point cloud models. In Proc. IEEE International Conference on Computer Vision (ICCV): 863–872
Kumar M, Bansal M, Kumar M (2020) 2D object recognition techniques: state-of-the-art work. Archives of Computational Methods in Engineering 5:1–15
Lee J, Rossi R, Kim S, Ahmed N, Koh E (2018) Attention models in graphs: A survey. arXiv preprint arXiv:1807.07984
Liu X, Han Z, Liu Y, Zwicker M (2019) Point2Sequence: learning the shape representation of 3D point clouds with an attention-based sequence to sequence network. In proc. AAAI Conference on Artificial Intelligence, 33:8778–8785
Liu JX, Ni BB, Li CY, Yang JC, Tian Q (2019) Dynamic points agglomeration for hierarchical point sets learning. In Proc. IEEE International Conference on Computer Vision (ICCV). Seoul, Korea (South): IEEE: 7546–7555
Liu S, Wang S, Liu X et al (2020) Fuzzy Detection aided Real-time and Robust Visual Tracking under Complex Environments. IEEE Transactions on Fuzzy Systems 99:1
Liu S, Wang S, Liu X, Gandomi AH, Daneshmand M, Muhammad K, de Albuquerque VHC (2021) Human memory update strategy: a multi-layer template update mechanism for remote visual monitoring. IEEE Transactions on Multimedia 99:1
Luciano L, Hamza A (2017) Deep learning with geodesic moments for 3D shape classification. Pattern Recog Lett 105:182–190
Luciano L, Hamza A (2018) Deep learning with geodesic moments for 3D shape classification. Pattern Recog Lett 105:182–190
Masoumi M, Li C, Hamza A (2016) A spectral graph wavelet approach for non rigid 3D shape retrieval. Pattern Recogn Lett 83:339–348
Masoumi M, Li C, Hamza A (2016) A spectral graph wavelet approach for non rigid 3D shape retrieval. Pattern Recogn Lett 83:339–348
Niepert M, Ahmed M, Kutzkov K (2016) Learning convolutional neural networks for graphs. In ICML, 2014–2023
Qi C, Su H, Mo K, Guibas L (2017) PointNet: deep learning on point sets for 3D classification and segmentation. In CVPR: 77–85
Qi C, Yi L, Su H, Guibas L (2017) PointNet++: deep hierarchical feature learning on point sets in a metric space. Adv Neural Inf Proces Syst 30:5099–5108
Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis & Machine Intelligence 39(6):1137–1149
Scarselli F, Gori M, Tsoi A, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE Trans Neural Netw 20(1):61–80
Simonovsky M (2017) Dynamic edge-conditioned filters in convolutional neural networks on graphs. In CVPR
Thomas H, Qi C, Deschaud J et al. (2019) KPConv: flexible and deformable convolution for point clouds. In Proc. ICCV
Velickovic P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. In Proc. 7th International Conference on Learning Representations (ICLR)
Verma N, Boyer E, Verbee J (2018) FeaStNet: feature-steered graph convolutions for 3D shape analysis. In CVPR, 2598–2606
Wang Y, Sun Y, Liu Z, Sarma S, Bronstein M, Solomon J (2018) Dynamic graph CNN for learning on point clouds. ACM Trans Graph 38(5):12
Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In CVPR, 7794–7803
Wang C, Samari B, Siddiqi K (2018) Local spectral graph convolution for point set feature learning. In Proc. the European Conference on Computer Vision (ECCV): 52–66
Wu W, Qi Z, Li F (2019) PointConv: deep convolutional networks on 3D point clouds. In CVPR
Wu W, Zhang Y, Wang D, Lei Y (2020) SK-Net: deep learning on point cloud via end-to-end discovery of spatial keypoints. In Proc. Thirty-Fourth AAAI Conference on Artificial Intelligence, 6422–6429
Xie J, Fang Y, Zhu F (2016) Deep shape: deep learned shape descriptor for 3D shape matching and retrieval. Comput Vis Pattern Recog
Xu B, Shen H, Cao Q, Cen K, Cheng X (2019) Graph convolutional networks using heat kernel for semi-supervised learning. In Proc. 28th International Joint Conference on Artificial Intelligence. Macao, China:1928–1934
Yan X, Zheng C, Li Z, Zhen S, Wang S, Cui S (2020) PointASNL: robust point clouds processing using nonlocal neural networks with adaptive sampling.In CVPR
Yi L, Su H, Guo X, Guibas L (2017) Syncspeccnn: synchronize spectral cnn for 3d shape segmentation. In CVPR: 6584–6592
Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions. In: Proc. International Conference on Learning Representations (ICLR)
Zhang D, He F, Tu Z, Zou L, Chen Y (2020) Pointwise geometric and semantic learning network on 3D point clouds. Integr Comput -Aided Eng 27(1):57–75
Acknowledgements
We would like to thank the anonymous reviewers for their helpful comments. The research presented in this paper is supported by a grant from NSFC (61702246), grants from research projects of Liaoning province (2019lsktyb-084, 2020JH4/10100045, LJ2020015) and a fund of Dalian Science and Technology (2019J12GX038).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interests/Competing interests
We declare that we have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Han, L., Lan, P., Shi, X. et al. Topological and geometrical joint learning for 3D graph data. Multimed Tools Appl 82, 15457–15474 (2023). https://doi.org/10.1007/s11042-022-13806-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13806-y