{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:59:25Z","timestamp":1760144365929,"version":"build-2065373602"},"reference-count":30,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T00:00:00Z","timestamp":1713139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of Hebei Province","award":["F2019201451"],"award-info":[{"award-number":["F2019201451"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Analyzing point clouds with neural networks is a current research hotspot. In order to analyze the 3D geometric features of point clouds, most neural networks improve the network performance by adding local geometric operators and trainable parameters. However, deep learning usually requires a large amount of computational resources for training and inference, which poses challenges to hardware devices and energy consumption. Therefore, some researches have started to try to use a nonparametric approach to extract features. Point-NN combines nonparametric modules to build a nonparametric network for 3D point cloud analysis, and the nonparametric components include operations such as trigonometric embedding, farthest point sampling (FPS), k-nearest neighbor (k-NN), and pooling. However, Point-NN has some blindness in feature embedding using the trigonometric function during feature extraction. To eliminate this blindness as much as possible, we utilize a nonparametric energy function-based attention mechanism (ResSimAM). The embedded features are enhanced by calculating the energy of the features by the energy function, and then the ResSimAM is used to enhance the weights of the embedded features by the energy to enhance the features without adding any parameters to the original network; Point-NN needs to compute the similarity between each feature at the naive feature similarity matching stage; however, the magnitude difference of the features in vector space during the feature extraction stage may affect the final matching result. We use the Squash operation to squeeze the features. This nonlinear operation can make the features squeeze to a certain range without changing the original direction in the vector space, thus eliminating the effect of feature magnitude, and we can ultimately better complete the naive feature matching in the vector space. We inserted these modules into the network and build a nonparametric network, Point-Sim, which performs well in 3D classification tasks. Based on this, we extend the lightweight neural network Point-SimP by adding some trainable parameters for the point cloud classification task, which requires only 0.8 M parameters for high performance analysis. Experimental results demonstrate the effectiveness of our proposed algorithm in the point cloud shape classification task. The corresponding results on ModelNet40 and ScanObjectNN are 83.9% and 66.3% for 0 M parameters\u2014without any training\u2014and 93.3% and 86.6% for 0.8 M parameters. The Point-SimP reaches a test speed of 962 samples per second on the ModelNet40 dataset. The experimental results show that our proposed method effectively improves the performance on point cloud classification networks.<\/jats:p>","DOI":"10.3390\/a17040158","type":"journal-article","created":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T08:08:12Z","timestamp":1713168492000},"page":"158","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Point-Sim: A Lightweight Network for 3D Point Cloud Classification"],"prefix":"10.3390","volume":"17","author":[{"given":"Jiachen","family":"Guo","sequence":"first","affiliation":[{"name":"School of Cyber Security and Computer, Hebei University, Baoding 071000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2070-465X","authenticated-orcid":false,"given":"Wenjie","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Cyber Security and Computer, Hebei University, Baoding 071000, China"}]}],"member":"1968","published-online":{"date-parts":[[2024,4,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"4338","DOI":"10.1109\/TPAMI.2020.3005434","article-title":"Deep Learning for 3D Point Clouds: A Survey","volume":"43","author":"Guo","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1109\/TPAMI.2019.2928550","article-title":"Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy","volume":"43","author":"Liang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., and Xia, T. (2017, January 21\u201326). Multi-view 3d object detection network for autonomous driving. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015, January 7\u201313). Multi-view Convolutional Neural Networks for 3D Shape Recognition. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Maturana, D., and Scherer, S. (October, January 28). VoxNet: A 3D Convolutional Neural Network for real-time object recognition. Proceedings of the 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany.","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref_6","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., and Xiao, J. (2015, January 7\u201312). 3d shapenets: A deep representation for volumetric shapes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Charles, R.Q., Su, H., Kaichun, M., and Guibas, L.J. (2017, January 21\u201326). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref_8","first-page":"5105","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_9","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Qureshi, S.A., Raza, S.E.A., Hussain, L., Malibari, A.A., Nour, M.K., Rehman, A.U., Al-Wesabi, F.N., and Hilal, A.M. (2022). Intelligent Ultra-Light Deep Learning Model for Multi-Class Brain Tumor Detection. Appl. Sci., 12.","DOI":"10.3390\/app12083715"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhang, R., Wang, L., Wang, Y., Gao, P., Li, H., and Shi, J. (2023). Parameter is not all you need: Starting from non-parametric networks for 3d point cloud analysis. arXiv.","DOI":"10.1109\/CVPR52729.2023.00517"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"12145","DOI":"10.1109\/JSEN.2019.2937089","article-title":"MVPointNet: Multi-view network for 3D object based on point cloud","volume":"19","author":"Zhou","year":"2019","journal-title":"IEEE Sens. J."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Le, T., and Duan, Y. (2018, January 18\u201323). Pointgrid: A deep network for 3d shape understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00959"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, Y., Tan, D.J., Navab, N., and Tombari, F. (2020, January 23\u201328). Softpoolnet: Shape descriptor for point cloud completion and classification. Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part III 16.","DOI":"10.1007\/978-3-030-58580-8_5"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Birdal, T., Deng, H., and Tombari, F. (2019, January 15\u201320). 3D point capsule networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00110"},{"key":"ref_16","first-page":"1","article-title":"Dynamic graph cnn for learning on point clouds","volume":"38","author":"Wang","year":"2019","journal-title":"ACM Trans. Graph. (Tog)"},{"key":"ref_17","unstructured":"Li, G., Muller, M., Thabet, A., and Ghanem, B. (November, January 27). Deepgcns: Can gcns go as deep as cnns?. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, Y., Hou, Y., Zhang, S., and Shan, J. (2019, January 15\u201320). Graph attention convolution for point cloud semantic segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01054"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wang, Y., Tan, D.J., Navab, N., and Tombari, F. (2022, January 18\u201324). Learning local displacements for point cloud completion. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00162"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201323). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8\u201314). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Cision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_22","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yang, J., Zhang, Q., Ni, B., Li, L., Liu, J., Zhou, M., and Tian, Q. (2019, January 15\u201320). Modeling point clouds with self-attention and gumbel subset sampling. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00344"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., and Koltun, V. (2021, January 11\u201317). Point transformer. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","article-title":"Pct: Point cloud transformer","volume":"7","author":"Guo","year":"2021","journal-title":"Comput. Vis. Media"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yu, X., Rao, Y., Wang, Z., Liu, Z., Lu, J., and Zhou, J. (2021, January 11\u201317). Pointr: Diverse point cloud completion with geometry-aware transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.01227"},{"key":"ref_27","unstructured":"Yang, L., Zhang, R., Li, L., and Xie, X. (2021, January 18\u201324). Simam: A simple, parameter-free attention module for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Virtual Event."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"11666","DOI":"10.1523\/JNEUROSCI.3414-05.2005","article-title":"Early and late mechanisms of surround suppression in striate cortex of macaque","volume":"25","author":"Webb","year":"2005","journal-title":"J. Neurosci."},{"key":"ref_29","unstructured":"Zhang, R., Fang, R., Zhang, W., Gao, P., Li, K., Dai, J., Qiao, Y., and Li, H. (2021). Tip-adapter: Training-free clip-adapter for better vision-language modeling. arXiv."},{"key":"ref_30","unstructured":"Uy, M.A., Pham, Q.H., Hua, B.S., Nguyen, T., and Yeung, S.K. (November, January 27). Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/4\/158\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:28:04Z","timestamp":1760106484000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/4\/158"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,15]]},"references-count":30,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["a17040158"],"URL":"https:\/\/doi.org\/10.3390\/a17040158","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2024,4,15]]}}}