一种面向服装样板图分类的图卷积神经网络

doi:10.3969/j.issn.1000-5641.2022.04.006

摘要/Abstract

摘要：

服装样板图的识别和分类是服装智能化生产和管理的重要技术. 提出了一种将服装样板图转化为图数据的建模法和一种能处理这类图数据的轻量级图神经网络GPC-GCN (Garment Pattern Classification Graph Convolutional Network). 所提出的图数据的建模法不但能够保留服装样板图中每个部件的形状信息, 还解决了服装样版图中服装部件可以随意放置的问题. 实验表明, 与既有的卷积神经网络和图神经网络相比较, 所提出的图数据建模法和图神经网络GPC-GCN对服装样板图的分类具有更优的性能.

关键词: 图卷积神经网络, 服装样板图, 图形分类

Abstract:

The identification and classification of garment patterns are important technologies for intelligent clothing production and management. This paper proposes a method to convert garment patterns into graphic data and subsequently proposes a lightweight graph neural network GPC-GCN (Garment Pattern Classification Graph Convolutional Network) that can process this graphic data. The proposed graph data modeling method can not only maintain information on the shape of each component in the garment pattern but also deal with the arbitrariness of the position of components in garment patterns. Experiments show that the proposed graph neural network GPC-GCN achieves a better result for the classification of garment patterns compared to convolutional neural networks and graph convolutional networks.

Key words: graph convolutional network, garment pattern, graph classification

中图分类号:

TP391.4

赵晓臻, 童卫青, 刘咏梅. 一种面向服装样板图分类的图卷积神经网络[J]. 华东师范大学学报（自然科学版）, 2022, 2022(4): 56-66.

Xiaozhen ZHAO, Weiqing TONG, Yongmei LIU. A graph convolutional neural network for garment pattern classification[J]. Journal of East China Normal University(Natural Science), 2022, 2022(4): 56-66.

图/表 11

图1

图2

图3

图4

表1

图5

表2

表3

图6

表4

表5

参考文献 26

1	孙明慧. 数字化服装产品设计可重用技术研究 [D]. 上海: 东华大学, 2008.
2	安立新. 服装款式图提取及其模式识别的研究 [D]. 上海: 东华大学, 2015.
3	LEE J, SUL I H. Construction of garment pattern shape information system using image analysis and shape recognition techniques. International Journal of Clothing Science and Technology, 2016, 28 (4): 543- 555.
4	ZHANG Z W, CUI P, ZHU W W. Deep learning on graphs: A survey [EB/OL]. (2020-03-17)[2020-12-10]. https://ieeexplore.ieee.org/document/9039675.
5	GORI M, MONFARDINI G, SCARSELLI F. A new model for learning in graph domains [C]// Proceedings of the 2005 IEEE International Joint Conference on Neural Networks. 2005: 729-734.
6	SHUMAN D I, NARANG S K, FROSSARD P, et al. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Processing Magazine, 2013, 30 (3): 83- 98.
7	BRUNA J B, ZAREMBA W, SZLAM A, et al. Spectral networks and deep locally connected networks on graphs [EB/OL]. (2020-02-20)[2020-10-11]. http://yann.lecun.com/exdb/publis/pdf/bruna-iclr-14.pdf.
8	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks [EB/OL]. (2017-02-22)[2020-12-09]. https://arxiv.org/pdf/1609.02907.pdf.
9	GILMER J, SCHOENHOLZ S S, RILEY P F, et al. Neural message passing for quantum chemistry [C]// Proceedings of the 34th International Conference on Machine Learning. 2017: 2053-2070.
10	SONG W P, XIAO Z P, WANG Y F, et al. Session-based social recommendation via dynamic graph attention networks [C]// Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining. 2019: 555-563.
11	CHEN X L, LI L J, LI F F, et al. Iterative visual reasoning beyond convolutions [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 7239-7248.
12	QI C R, SU H, MO K, et al. PointNet: Deep learning on point sets for 3D classification and segmentation [C]// Proceedings of the 30th IEEE conference on Computer Vision and Pattern Recognition. 2017: 77-85.
13	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. 2017: 5105-5114.
14	LIU Y C, FAN B, XIANG S M, et al. Relation-shape convolutional neural network for point cloud analysis [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 8887-8896.
15	SU H, JAMPANI V, SUN D Q, et al. SPLATNet: Sparse lattice networks for point cloud processing [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 2530-2539.
16	THOMAS H, QI C R, DESCHAUD J E, et al. KPConv: Flexible and deformable convolution for point clouds [C]// Proceedings of the IEEE International Conference on Computer Vision. 2019: 6410-6419.
17	MONTI F, BOSCAINI D, MASCI J, et al. Geometric deep learning on graphs and manifolds using mixture model CNNs [C]// Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition. 2017: 5425-5434.
18	FEY M, LENSSEN J E, WEICHERT F, et al. SplineCNN: Fast geometric deep learning with continuous B-spline kernels [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 869-877.
19	GAO H Y, JI S W. Graph U-Nets [C]// Proceedings of the 36th International Conference on Machine Learning. 2019: 2083-2092.
20	YING R, YOU J, MORRIS C, et al. Hierarchical graph representation learning with differentiable pooling [C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018: 4805–4815.
21	LEE J, LEE I, KANG J. Self-attention graph pooling [C]// Proceedings of the 36th International Conference on Machine Learning. 2019: 6661-6670.
22	HE K, ZHANG X Y, REN S Q, et al. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification [C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. 2015: 1026-1034.
23	PEITGEN H O, JÜRGENS H, SAUPE D. Chaos and Fractals [M]. 2nd ed. New York: Springer-Verlag, 2004.
24	ZHANG H, WU C R, ZHANG Z Y, et al. ResNeSt: Split-Attention networks [EB/OL]. (2020-12-30)[2021-01-08]. https://arxiv.org/pdf/2004.08955.pdf.
25	XU K, HU W H, LESKOVEC J, et al. How powerful are graph neural networks? [EB/OL]. (2019-02-22) [2020-12-11]. https://arxiv.org/pdf/1810.00826.pdf.
26	WU Z Q, RAMSUNDAR B, FEINBERG E N, et al. MoleculeNet: A benchmark for molecular machine learning. Chemical Science, 2018, 9 (2): 513- 530.

组件	输出	参数设置
GMMConv1	$\left\|\alpha \right\|=32$	$ \left\|A\right\|=2\times 6 $
		$ \left\|C\right\|=1\times 4 $
		$ J=16 $
SAG Pooling1	$ \left\|V\right\|=0.4N $	$ \left\|A\right\|=1\times 6 $
GMMConv2	$\left\|\alpha \right\|=64$	$ \left\|A\right\|=2\times 6 $
		$ \left\|C\right\|=1\times 4 $
		$ J=32 $
SAG Pooling2	$ \left\|V\right\|=0.16N $	$ \left\|A\right\|=1\times 6 $
GMMConv3	$\left\|\alpha \right\|=128$	$ \left\|A\right\|=2\times 6 $
		$ \left\|C\right\|=1\times 4 $
		$ J=64 $
全连接层	$ \left\|c\right\|=C $ , $ C $ 为类型数	$ \left\|A\right\|=1\times C $ , $ C $ 为类型数

数据集	大衣样板数/幅	长裙样板数/幅	长大衣样板数/幅	裤子样板数/幅	衬衣样板数/幅	短裙样板数/幅	上衣样板数/幅	样板数总计/幅
GPDSet-A	24128	20544	12592	3472	4960	4736	6896	77328
GPDSet-B	10016	30896	10592	14992	0	6416	11024	83936

神经网络	Top 1 准确率	平均推断时间/ms
ResNeSt50	0.908	15.6
GIN	0.342	5.3
GCN	0.452	4.5
GPC-GCN	0.955	9.1

神经网络	Top 1 准确率	平均推断时间/ms
ResNeSt50	0.511	15.6
GIN	0.287	5.3
GCN	0.283	4.5
GPC-GCN	0.715	9.1

神经网络	Top 1 准确率	平均推断时间/ms
ResNeSt50	0.133	15.6
GIN	0.271	5.3
GCN	0.282	4.5
GPC-GCN	0.694	9.1