Neural architecture search for 3D model classification based on adaptive smoothness strategy

ZHOU Peng; YANG Jun

doi:10.11959/j.issn.2096-6652.202417

您当前的位置：

首页 >

文章列表页 >

Neural architecture search for 3D model classification based on adaptive smoothness strategy

Papers and Reports | 更新时间：2024-08-06

- Neural architecture search for 3D model classification based on adaptive smoothness strategy
- Chinese Journal of Intelligent Science and Technology Vol. 6, Issue 2, Pages: 272-280(2024)
- 作者机构：
  
  1.兰州交通大学电子与信息工程学院，甘肃兰州 730070
  2.兰州交通大学测绘与地理信息学院，甘肃兰州 730070
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(42261067);The Natural Science Foundation of Gansu Province(22JR11RA157)
- DOI：10.11959/j.issn.2096-6652.202417
  CLC： TP391.41
- Received：02 January 2024，
  
  Revised：2024-05-14，
  
  Published：15 June 2024
- 稿件说明：
移动端阅览
周鹏,杨军.基于自适应平滑度策略的三维模型分类神经架构搜索[J].智能科学与技术学报,2024,06(02):272-280.

ZHOU Peng,YANG Jun.Neural architecture search for 3D model classification based on adaptive smoothness strategy[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):272-280.
周鹏,杨军.基于自适应平滑度策略的三维模型分类神经架构搜索[J].智能科学与技术学报,2024,06(02):272-280. DOI： 10.11959/j.issn.2096-6652.202417.

ZHOU Peng,YANG Jun.Neural architecture search for 3D model classification based on adaptive smoothness strategy[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):272-280. DOI： 10.11959/j.issn.2096-6652.202417.

摘要

针对人工设计三维模型分类网络架构过度依赖专家经验且泛化能力较差的问题，提出了一种自适应平滑度策略的神经架构搜索方法。首先，使用改进候选操作选择策略和连续松弛化方法将离散的搜索空间连续化，并利用权重共享机制提高搜索效率。其次，在损失函数中添加自适应平滑度策略的正则化，由温度参数控制损失函数的平滑程度。最后，使用指数归一化方法计算损失函数，以避免损失值溢出。在三维点云数据集和蛋白质间相互作用数据集上的实验结果表明，在相同的训练样本和迭代次数下，自适应平滑度策略的神经架构搜索方法的分类准确率更高，性能更稳定。

Abstract

Aiming at the problem of poor generalization ability in hand-crafted architectures that overly rely on expert experience

a neural network architecture search method with an adaptive smoothness strategy was proposed. Firstly

an improved candidate operation selection strategy and a continuous relaxation method were used to convert discrete search space into continuous space

and a weight-sharing mechanism was employed to enhance search efficiency. Secondly

a regularization operation with an adaptive smoothness strategy was added to the loss function

whose smoothness degree was controlled by a temperature parameter. Finally

the loss function was calculated using an exponential normalization method to avoid loss value overflow. Experimental results on 3D point cloud datasets and protein-protein interaction datasets showed that the proposed method achieved higher classification accuracy and more stable performance under the same training samples and iterations.

关键词

Keywords

references

郑伟斌, 练国富, 张学明, 等. 基于主成分分析和特征图匹配的点云配准方法[J]. 智能科学与技术学报, 2023, 5(4): 543-552.

ZHENG W B, LIAN G F, ZHANG X M, et al. Point cloud registration method based on principal component analysis and feature map matching[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(4): 543-552.

于航, 付彦伟, 姜柏言, 等. 基于少量图像的三维重建综述[J]. 智能科学与技术学报, 2022, 4(4): 544-559.

YU H, FU Y W, JIANG B Y, et al. A survey of image-based few-shot 3D reconstruction[J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(4): 544-559.

缪青海, 王兴霞, 杨静, 等. 从基础智能到通用智能: 基于大模型的GenAI和AGI之现状与展望[J]. 自动化学报, 2024, 50(4): 674-687.

MIAO Q H, WANG X X, YANG J, et al. From foundation intelligence to general intelligence: the state-of-art and perspectives of GenAI and AGI based on foundation models[J]. Acta Automatica Sinica, 2024, 50(4): 674-687.

李建明, 陈斌, 孙晓飞. 熵启发的分级可微分网络架构搜索[J]. 哈尔滨工业大学学报, 2021, 53(8): 22-28.

LI J M, CHEN B, SUN X F. Multi-level differentiable architecture search with heuristic entropy[J]. Journal of Harbin Institute of Technology, 2021, 53(8): 22-28.

LI G H, QIAN G C, DELGADILLO I C, et al. SGAS: sequential greedy architecture search[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2020: 1617-1627.

周鹏, 杨军. 采用神经网络架构搜索的三维模型分类[J]. 计算机辅助设计与图形学学报, 2022, 34(5): 722-733.

ZHOU P, YANG J. 3D model classification based on neural architecture search[J]. Journal of Computer-Aided Design & Computer Graphics, 2022, 34(5): 722-73.

周鹏, 杨军. 基于边缘特征的图神经网络架构搜索[J]. 兰州交通大学学报, 2022, 41(6): 44-53.

ZHOU P, YANG J. Graph neural architecture search based on edge features[J]. Journal of Lanzhou Jiaotong University, 2022, 41(6): 44-53.

ZOPH B, LE Q V. Neural architecture search with reinforcement learning[EB]. arXiv preprint, 2016, arXiv: 1611.01578.

REAL E, MOORE S, SELLE A, et al. Large-scale evolution of image classifiers[C]//Proceedings of the 34th International Conference on Machine Learning. New York: ACM, 2017: 2902-2911.

LIU H X, SIMONYAN K, YANG Y M. DARTS: differentiable architecture search[EB]. arXiv preprint, 2018, arXiv: 1806.09055.

LIANG H W, ZHANG S F, SUN J C, et al. DARTS+: improved differentiable architecture search with early stopping[EB]. arXiv preprint, 2019, arXiv: 1909.06035.

CHEN X, XIE L X, WU J, et al. Progressive differentiable architecture search: bridging the depth gap between search and evaluation[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2019: 1294-1303.

CHU X X, ZHOU T B, ZHANG B, et al. Fair DARTS: eliminating unfair advantages in differentiable architecture search[C]//Proceedings of the 2020 European Conference on Computer Vision. Cham: Springer, 2020: 465-480.

CHU X X, WANG X X, ZHANG B, et al. DARTS-: robustly stepping out of performance collapse without indicators[EB]. arXiv preprint, 2020, arXiv: 2009.01027.

ZELA A, ELSKEN T, SAIKIA T, et al. Understanding and robustifying differentiable architecture search[EB]. arXiv preprint, 2019, arXiv: 1909.09656.

LI Y X, YANG Z H , WANG Y H, et al. Adapting neural architectures between domains[C]//Proceedings of the 34th Conference on Neural Information Processing Systems. New York: ACM, 2020: 789-798.

LIU L Y, WEN Z W, LIU S W, et al. MixSearch: searching for domain generalized medical image segmentation architectures[EB]. arXiv preprint, 2021, arXiv: 2102.13280.

YE P, LI B P, LI Y K, et al. β-DARTS: beta-decay regularization for differentiable architecture search[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2022: 10864-10873.

HERRMANN C, BOWEN R S, ZABIH R. Channel selection using gumbel softmax[C]//Proceedings of the 2020 European Conference on Computer Vision. Cham: Springer, 2020: 241-257.

QI C R, YI L, SU H, et al. PointNet++: deep hierarchical feature learning on point sets in a metric space[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York: ACM, 2017: 5105-5114.

THOMAS H, QI C R, DESCHAUD J E, et al. KPConv: flexible and deformable convolution for point clouds[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2019: 6410-6419.

WANG Y, SUN Y B, LIU Z W, et al. Dynamic graph CNN for learning on point clouds[J]. ACM Transactions on Graphics, 2019, 38(5): 146-160.

CHU X X, ZHANG B. Noisy differentiable architecture search[EB]. arXiv preprint, 2020, arXiv: 2005.03566.

CAI S F, LI L, HAN X Z, et al. Automatic relation-aware graph network proliferation[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2022: 10853-10863.

LI G H, MÜLLER M, THABET A, et al. DeepGCNs: can GCNs go as deep as CNNs? [C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2019: 9266-9275.

HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[EB]. arXiv preprint, 2017, arXiv: 1706.02216.

BASTIDAS A A, TANG H L. Channel attention networks[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway: IEEE Press, 2019: 881-888.

Views

299

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A survey of 3D object detection algorithms

A survey on evolutionary ensemble learning algorithm

Cerberus: a cross-site social bot detection system based on deep learning

Related Author

Zhe HUANG

Yongcai WANG

Deying LI

Yi HU

Boyang QU

Jing LIANG

Jie WANG

Yanli WANG

Related Institution

School of Information, Renmin University of China

Key Laboratory of Police Internet of Things Application Ministry of Public Security

School of Electrical Engineering, Zhengzhou University

School of Electronic and Information, Zhongyuan University of Technology

Postal code：100079
Tel：（010）53879206 Email：cjist@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：161982 Visits Today：145

⁰