结合迁移引导和双向循环结构GAN的零样本文本识别

doi:10.16451/j.cnki.issn1003-6059.202012003

摘要
图/表
参考文献(27)
相关文章 (1)

全文: PDF (2387 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

为了提高基于生成对抗网络(GAN)的零样本识别方法的识别精度,提出结合迁移引导和双向循环结构GAN的零样本文本识别方法.构造双向循环结构GAN以提高模型的生成能力,生成的伪特征更接近输入的真实特征.引入迁移引导学习的思想,使用迁移后的文本代替可见类文本训练模型,提高不可见类文本的识别精度.增加有效的正则化项,使生成器在训练过程中生成的结果具有多样性,提高生成模型的稳定性.在数据集上的实验表明,文中方法可提高识别精度,具有较好的泛化性能,容易拓广到其它应用中.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张桂梅
	龙邦耀
	鲁飞飞

关键词 ：迁移引导, 双向循环结构, 零样本学习, 文本识别

Abstract：

To improve the recognition accuracy of zero-shot recognition methods based on generative adversarial network(GAN),a zero-shot text recognition method combining transfer guidance and bidirectional cycle structure GAN is proposed.Bidirectional cycle structure GAN is constructed to improve the generation ability of the model,thus the generated pseudo features are closer to the real features of the input.The concept of transfer guided learning is introduced,and the model is trained by the transfer text instead of the seen text to improve the recognition accuracy of the unseen text.By adding an effective regularization term,the generator generates diverse results during the training process,and thus the stability of the generated model is improved.The experiment shows that the proposed method improves the accuracy of zero-shot recognition task with high generalization performance and it can be easily extended to other applications.

Key words： Transfer Guide Bidirectional Cycle Structure Zero-Shot Learning Text Recognition

收稿日期: 2020-07-22

基金资助:

国家自然科学基金项目(No.61462065)资助

通讯作者: 张桂梅,博士,教授,主要研究方向为计算机视觉、图像处理、模式识别.E-mail:guimei.zh@163.com.

作者简介: 龙邦耀,硕士研究生,主要研究方向为计算机视觉、图像处理、模式识别.E-mail:lby609527215@163.com;鲁飞飞,硕士研究生,主要研究方向为计算机视觉、图像处理、模式识别.E-mail:1323568545@qq.com.

引用本文:

张桂梅, 龙邦耀, 鲁飞飞. 结合迁移引导和双向循环结构GAN的零样本文本识别[J]. 模式识别与人工智能, 2020, 33(12): 1083-1096. ZHANG Guimei, LONG Bangyao, LU Feifei. Zero-Shot Text Recognition Combining Transfer Guide and Bidirectional Cycle Structure GAN. , 2020, 33(12): 1083-1096.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202012003 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2020/V33/I12/1083

[1] LAROCHELLE H,ERHAN D,BENGIO Y.Zero-Data Learning of New Tasks//Proc of the 23rd National Conference on Artificial Intelligence.Palo Alto,USA:AAAI Press,2008:646-651.
[2] LAMPERT C H,NICKISCH H,HARMELING S.Attribute-Based Classification for Zero-Shot Visual Object Categorization.IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(3):453-465.
[3] LIU M X,ZHANG D Q,CHEN S C.Attribute Relation Learning for Zero-Shot Classification.Neurocomputing,2014,139:34-46.
[4] 吴凡,王康.基于属性平衡正则化的深度零样本学习.计算机应用与软件,2018,35(10):165-170.
(WU F,WANG K.Deep Zero-Shot Learning Based on Attribute Balancing Regularization.Computer Applications and Software,2018,35(10):165-170.)
[5] ROMERA-PAREES B,TORR P H S.An Embarrassingly Simple Approach to Zero-Shot Learning//FERIS R S,LAMPERT C,PARIKH D,eds.Visual Attributes.Berlin,Germany:Springer,2017:11-30.
[6] CHANGPINYO S,CHAO W L,GONG B Q,et al.Synthesized Classifiers for Zero-Shot Learning//Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2016:5327-5336.
[7] 张鲁宁,左信,刘建伟.零样本学习研究进展.自动化学报,2020,46(1):1-23.
(ZHANG L N,ZUO X,LIU W J.Research and Development on Zero-Shot Learning.Acta Automatica Sinica,2020,46(1):1-23.)
[8] ELHOSEINY M,SALEH B,ELGAMMAL A.Write a Classifier:Zero-Shot Learning Using Purely Textual Descriptions//Proc of the IEEE International Conference on Computer Vision.Washington,USA:IEEE,2013:2584-2591.
[9] QIAO R Z,LIU L Q,SHEN C H,et al.Less Is More:Zero-Shot Learning from Online Textual Documents with Noise Suppression//Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2016:2249-2257.
[10] 冀中,孙涛,于云龙.一种基于直推判别字典学习的零样本分类方法.软件学报,2017,28(11):2961-2970.
(JI Z,SUN T,YU Y L.Transductive Discriminative Dictionary Learning Approach for Zero-Shot Classification.Journal of Software,2017,28(11):2961-2970.)
[11] ELHOSEINY M,ELGAMMAL A,SALEH B.Write a Classifier:Predicting Visual Classifiers from Unstructured Text.IEEE Transa-ctions on Pattern Analysis and Machine Intelligence,2017,39(12):2539-2553.
[12] ELHOSEINY M,ZHU Y Z,ZHANG H,et al.Link the Head to the "Beak":Zero-Shot Learning from Noisy Text Description at Part Precision//Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2017:6288-6297.
[13] SALTON G,BUCKLEY C.Term-Weighting Approaches in Automatic Text Retrieval.Information Processing and Management,1988,24(5):513-523.
[14] GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative Adversarial Nets//Proc of the 27th International Conference on Neural Information Processing Systems.Cambridge,USA:The MIT Press,2014,II:2672-2680.
[15] ZHU Y Z,ELHOSEINY M,LIU B C,et al.A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2018:1004-1013.
[16] ODENA A,OLAH C,SHLENS J.Conditional Image Synthesis with Auxiliary Classifier GANs//Proc of the 34th International Conference on Machine Learning.Berlin,Germany:Springer,2017:2642-2651.
[17] ELHOSEINY M,ELFEKI M.Creativity Inspired Zero-Shot Learning//Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2019:5784-5793.
[18] ZHU J Y,PARK T,LSOLA P,et al.Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Betworks//Proc of the IEEE International Conference on Computer Vision.Washington,USA:IEEE,2017:2242-2251.
[19] CHEN Z,LI J J,LUO Y D,et al.CANZSL:Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language//Proc of the IEEE Winter Conference on Applications of Computer Vision.Washington,USA:IEEE,2020:874-883.
[20] MAO Q,LEE H Y,TSENG H Y,et al.Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2019:1429-1437.
[21] ARJOVSKY M,CHINTALA S,BOTTOU L.Wasserstein GAN[C/OL].[2020-06-25]. https://128.84.21.199/pdf/1701.07875v1.pdf.
[22] WEI X,GONG B Q,LIU Z X,et al.Improving the Improved Training of Wasserstein GANs:A Consistency Term and Its Dual Effect[C/OL].[2020-06-25].https://arxiv.org/pdf/1803.01541.pdf.
[23] GULRAJANI I,AHMED F,ARJOVSKY M,et al.Improved Trai-ning of Wasserstein GANs[C/OL].[2020-06-25].https://arxiv.org/pdf/1704.00028.pdf.
[24] AKTÜRK E,BA?CI G B,SEVER R.Is Sharma-Mittal Entropy Really a Step Beyond Tsallis and Renyi Entropies[C/OL].[2020-06-25].https://arxiv.org/pdf/cond-mat/0703277.pdf.
[25] GUPTA H C,SHARMA B D.On Non-additive Measures of Inaccuracy.Czechoslovak Mathematical Journal,1976,26(4):584-595.
[26] 兰红,方治屿.零样本图像识别.电子与信息学报,2020,42(5):1188-1200.
(LAN H,FANG Z Y.Recent Advances in Zero-Shot Learning.Journal of Electronics and Information Technology,2020,42(5):1188-1200.)
[27] CHAO W L,CHANGPINYO S,GONG B Q,et al.An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild//Proc of the European Conference on Computer Vision.Berlin,Germany:Springer,2016:52-68.