一种基于注意力机制的无监督商标检索方法

梁观术; 曹江中; 戴青云; 黄云飞

doi:10.12052/gdutxb.200027

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

一种基于注意力机制的无监督商标检索方法

更新时间：2026-05-27

- 一种基于注意力机制的无监督商标检索方法
- An Unsupervised Trademark Retrieval Method Based on Attention Mechanism
- 广东工业大学学报 2020年37卷第6期页码：41-49
- 作者机构：
  
  1. 广东工业大学信息工程学院,广东,广州,510006
  2. 广东技术师范大学广东省知识产权大数据重点实验室,广东,广州,510665
- 作者简介：
  
  梁观术(1993–)，男，硕士研究生，主要研究方向为计算机视觉
  曹江中(1976–)，男，副教授，博士，主要研究方向为计算机视觉、机器学习、知识产权大数据，E-mail: cjz510@gdut.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(U1701266);广东省自然科学基金资助项目(2018A030313751);广东省知识产权大数据重点实验室项目(2018B030322016)
- DOI：10.12052/gdutxb.200027
  中图分类号： TP391.4
- 网络首发：2020-11-02，
  
  纸质出版：2020
- 稿件说明：
移动端阅览
梁观术, 曹江中, 戴青云, 黄云飞. 一种基于注意力机制的无监督商标检索方法[J]. 广东工业大学学报, 2020, 37(6): 41-49.

Liang Guan-shu, Cao Jiang-zhong, Dai Qing-yun, et al. An Unsupervised Trademark Retrieval Method Based on Attention Mechanism[J]. 2020, 37(6): 41-49.
梁观术, 曹江中, 戴青云, 黄云飞. 一种基于注意力机制的无监督商标检索方法[J]. 广东工业大学学报, 2020, 37(6): 41-49. DOI： 10.12052/gdutxb.200027.

Liang Guan-shu, Cao Jiang-zhong, Dai Qing-yun, et al. An Unsupervised Trademark Retrieval Method Based on Attention Mechanism[J]. 2020, 37(6): 41-49. DOI： 10.12052/gdutxb.200027.

摘要

针对现有商标特征提取方法无法有效捕捉重点区域的关键信息和图像标注成本过高的问题

提出一种基于注意力机制的无监督商标检索方法。该方法基于实例区分算法

将注意力模块同时运用在神经网络特征映射层的空间维度和通道维度上

通过对各个通道进行权重的分配以及对空间变换参数的学习

增强无监督网络的特征表达能力。该方法在公开的商标数据集上进行了验证

实验表明检索效果优于传统的商标检索方法

甚至优于一些有监督商标检索方法。

Abstract

In order to solve the deficiency in capturing key information in key areas and the high cost of image annotation in the existing trademark retrieval methods

this paper proposes an unsupervised trademark retrieval method based on attention mechanism. The method applies the attention module to both the spatial dimension and the channel dimension of the feature map layer in the neural network of instance discrimination. Through assigning weights to each channel and learning the spatial transformation parameters

the unsupervised network improve its ability of extracting feature. We further validate the effectiveness of our method on the public trademark datasets and the experiments demonstrate that the proposed method in the paper is better than the traditional trademark retrieval methods

and even surpasses some supervised trademark retrieval methods.

关键词

Keywords

references

PHAN R, ANDROUTSOS D. Content-based retrieval of logo and trademarks in unconstrained color image databases using color edge gradient co-occurrence histograms [J]. Computer Vision and Image Understanding, 2010, 114(1): 66-84.

LAM C, WU J, MEHTRE B. STAR−A system for trademark archival and retrieval [J]. World Patent Information, 1996, 4(18): 249-249.

OJALA T, PIETIKINEN M, MENP T. A generalized local binary pattern operator for multiresolution gray scale and rotation invariant texture classification[C]//Proceedings of the International Conference on Advances in Pattern Recognition. Brazil: Springer, 2001: 399-408.

OJALA T, PIETIKAINEN M, MAENPAA T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.

OLIVA A, TORRALBA A. Modeling the shape of the scene: a holistic representation of the spatial envelope [J]. International Journal of Computer Vision, 2001, 42(3): 145-175.

SIVIC J, ZISSERMAN A. Video Google: A text retrieval approach to object matching in videos[C]// Ninth IEEE International Conference on Computer Vision. France: IEEE, 2003: 1470-1477.

LOWE D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

HER I, MOSTAFA K, HUNG H K. A hybrid trademark retrieval system using four-gray-level zernike moments and image compactness indices [J]. International Journal of Image Processing (IJIP), 2011, 4(6): 631-646.

ZHANG H, WU J X. A survey on unsupervised image retrieval using deep features [J]. Journal of Computer Research and Development, 2018, 55(9): 1829-1842.

TURSUN O, AKER C, KALKAN S. A large-scale dataset and benchmark for similar trademark retrieval[J]. arXiv preprint arXiv: 170105766, 2017.

PEREZ C A, ESTVEZ P A, GALDAMES F J, et al. Trademark image retrieval using a combination of deep convolutional neural networks[C]// Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro: IEEE, 2018: 1-7.

WU Z, XIONG Y, YU S X, et al. Unsupervised feature learning via non-parametric instance discrimination[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 3733-3742.

BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv: 14090473, 2014.

WOO S, PARK J, LEE J-Y, et al. Cbam: convolutional block attention module[C]// Proceedings of the Proceedings of the European Conference on Computer Vision. Munich: ECCV, 2018: 13-19.

GUTMANN M, HYVÄRINEN A. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models[J]. Journal of Machine Learning Research, 2010, 9: 297-304.

YANG Z, YANG D, DYER C, et al. Hierarchical attention networks for document classification[C]// Proceedings of the Association for Computational Linguistics. North American: human language technologies, 2016: 1480-1489.

ZHOU G, ZHU X, SONG C, et al. Deep interest network for click-through rate prediction[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery Data Mining. London: ACM, 2018: 1059-1068.

KIM S, HORI T, WATANABE S. Joint CTC-attention based end-to-end speech recognition using multi-task learning[C]// Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). New Orleans, LA: IEEE, 2017: 4835-4839.

ZHU Y, LI R, YANG Y, et al. Learning cascade attention for fine-grained image classification[J]. Neural Networks, 2020, 122: 174-182.

FU J, ZHENG H, MEI T. Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition[C]// IEEE Conference on Computer Vision Pattern Recognition. Honolulu, HI: IEEE, 2017: 4438-4446.

HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141.

LASKAR Z, KANNALA J. Context aware query image representation for particular object retrieval[C]//Proceedings of the Scandinavian Conference on Image Analysis. Scandinavian: Springer, 2017: 88-99.

JADERBERG M, SIMONYAN K, ZISSERMAN A. Spatial transformer networks[C]// Proceedings of the Advances in Neural Information Processing Systems. Lake tahoe Nevada: NIPS, 2015: 2017-2025.

CHEN L, ZHANG H, XIAO J, et al. SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI: IEEE, 2017: 5659-5667.

WANG F, XIANG X, CHENG J, et al. Normface: L2 hypersphere embedding for face verification[C]// Proceedings of International Conference on Multimedia. Multimedia: ACM, 2017: 1041-1049.

PARIKH N, BOYD S. Proximal algorithms [J]. Foundations and Trends® in Optimization, 2014, 1(3): 127-239.

HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2016: 770-778.

LEI Z, FUZONG L, BO Z. A CBIR method based on color-spatial feature[C]//Proceedings of IEEE Region 10 Conference. Cheju Island: IEEE, 1999: 166-169.

DOUZE M, JGOU H, SANDHAWALIA H, et al. Evaluation of gist descriptors for web-scale image search[C]// Proceedings of the ACM International Conference on Image and Video. Retrieval. Santorini Island: ACM, 2009: 1-8.

RUSIOL M, LLADS J. Efficient logo retrieval through hashing shape context descriptors[C]//Proceedings of the 9th IAPR International Workshop on Document Analysis Systems. Boston: ACM, 2010: 215-222.

BAY H, ESS A, TUYTELAARS T, et al . Speeded-up robust features (SURF) [J ] . Computer Vision and Image Understanding, 2008, 110(3): 346-359.

DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//proceedings of Conference on Computer Vision and Pattern Recognition. California: IEEE, 2005: 886-893.

VURAL M F, YARDIMCI Y, TEMIZEI A. Registration of multispectral satellite images with orientation-restricted SIFT[C]//Proceedings of IEEE International Geoscience and Remote Sensing Symposium. Cape Town: IEEE, 2009: 243-246.

AKER C, TURSUN O, KALKAN S. Analyzing deep features for trademark retrieval[C]//Signal Processing and Communications Applications Conference. Antalya: IEEE, 2017: 1-4.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[C]// Proceedings of the Advances in neural information processing systems. Curran Associates Inc: NIPS, 2012: 1097-1105.

SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA: IEEE, 2015: 1-9.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv Preprint arXiv: 14091556, 2014.

TURSUN O, DENMAN S, SRIDHARAN S, et al. Enhancing feature invariance with learned image transformations for image retrieval[J]. arXiv Preprint arXiv: 200201642, 2020.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于注意力机制的无监督GAN多聚焦图像融合

基于隐藏特征的点云模块

基于语义融合特征的多人像语义分割方法

具守恒量波动方程的循环双子网物理信息神经网络

人工噪声辅助无人机太赫兹安全通信的鲁棒设计