基于共享特征相对属性的零样本图像分类

doi:10.11999/JEIT161133

Abstract
Figure/Table
References (17)
Related Citation (1)

Download: PDF (2369 KB)
Export: BibTeX | EndNote (RIS)

Abstract

Most algorithms of the zero-shot image classification with relative attributes do not consider the relationship between attributes and classes, therefore a new relative attributes method based on shared features is proposed for zero-shot image classification. In analogy to the multi-task learning, the object classifier and attribute classifier are simultaneously learned in this method, from which a shared sub-space of lower dimensional features is obtained to mine the relationship between attributes and classes. Inspired by the success of shared features, a novel relative attributes model based on shared features is proposed to promote the performance of the relationship between attributes and classes, in which the ranking function per attribute is learned by using shared features. In addition, the novel relative attributes model based on shared features is applied to zero-shot image classification, which yields high accuracy due to the shared features included. Experimental results demonstrate that the proposed method can achieve high relative attributes learning efficiency and zero-shot image classification accuracy.

Key words： Relative attribute Multi-task learning Shared features Zero-shot image classification

Received: 25 October 2016 Published: 14 April 2017

PACS:

TP18

Fund:

The National Natural Science Foundation of China (41501485)

Corresponding Authors: QIAO Xue E-mail: qiaoxuecumt@163.com

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	QIAO Xue
	PENG Chen
	DUAN He
	ZHANG Yuyao

Cite this article:

QIAO Xue,PENG Chen,DUAN He等. Shared Features Based Relative Attributes for Zero-shot Image Classification[J]. JEIT, 2017, 39(7): 1563-1570.

URL:

http://jeit.ie.ac.cn/EN/10.11999/JEIT161133 OR http://jeit.ie.ac.cn/EN/Y2017/V39/I7/1563

[1]	GAN C, YANG T, and GONG B. Learning attributes equals multi-source domain generalization[C]. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016: 87-97.
[2]	QIN Jie, WANG Yunhong, LIU Li, et al. Beyond semantic attributes: Discrete latent attributes learning for zero-shot recognition[J]. IEEE Signal Processing Letters, 2016, 23(11): 1667-1671. doi: 10.1109/LSP.2016.2612247.
[3]	PARIKH D and GRAUMAN K. Relative attributes[C]. IEEE International Conference on Computer Vision, Barcelona, Spain, 2011: 503-510.
[4]	YANG X, ZHANG T, XU C, et al. Deep relative attributes[J]. IEEE Transactions on Multimedia, 2016, 18(9): 1832-1842. doi: 10.1109/TMM.2016.2582379.
[5]	CHEN L, ZHANG Q, and LI B X. Predicting multiple attributes via relative multi-task learning[C]. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014: 1027-1034.
[6]	和华, 杜兰, 徐丹蕾, 等. 基于多任务复数因子分析模型的雷达高分辨距离像识别方法[J]. 电子与信息学报, 2015, 37(10): 2307-2313. doi:10.11999/JEIT141591.
	HE Hua, DU Lan, XU Danlei, et al. Radar HRRP target recognition method based on multi-task learning and complex factor analysis[J]. Journal of Electronics & Information Technology, 2015, 37(10): 2307-2313. doi: 10.11999/JEIT141591.
[7]	HWANG S J, SHA F, and GRAUMAN K. Sharing features between objects and their attributes[C]. IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 2011: 1761-1768.
[8]	LAMPERT C H, NICKISCH H, and HARMELING S. Attribute-based classification for zero-shot visual object categorization[J]. Pattern Analysis and Machine Intelligence, 2014, 36(3): 453-465. doi: 10.1109/TPAMI.2013.140.
[9]	ARGYRIOU A, EVGENIOU T, and PONTIL M. Convex multi-task feature learning[J]. Machine Learning, 2008, 73(3): 243-272. doi: 10.1007/s10994-007-5040-8.
[10]	SHI C, RUAN Q, AN G, et al. Hessian semi-supervised sparse feature selection based on L2,1/2-matrix norm[J]. IEEE Transactions on Multimedia, 2015, 17(1): 16-28. doi:10.1109/ TMM.2014.2375792.
[11]	李秀友, 薛永华, 董云龙, 等. 基于迭代凸优化的恒模波形合成方法[J]. 电子与信息学报, 2015, 37(9): 2171-2176. doi: 10.11999/JEIT141593.
	LI Xiuyou, XUE Yonghua, DONG Yunlong, et al. Constant modulus waveform synthesis based on iterative convex optimization[J]. Journal of Electronics & Information Technology, 2015, 37(9): 2171-2176. doi: 10.11999/ JEIT141593.
[12]	YANG Z M, WU H J, LI C N, et al. Least squares recursive projection twin support vector machine for multi-class classification[J]. International Journal of Machine Learning & Cybernetics, 2016, 7(3): 1-16. doi: 10.1007/s13042-015- 0394-x.
[13]	及歆荣, 侯翠琴, 侯义斌. 无线传感器网络下线性支持向量机分布式协同训练方法研究[J]. 电子与信息学报, 2015(3): 708-714. doi:10.11999/JEIT140408
	JI Xinrong, HOU Cuiqin, and HOU Yibin. Research on the distributed training method for linear SVM in WSN[J]. Journal of Electronics & Information Technology, 2015, 37(3): 708-714. doi:10.11999/JEIT140408.
[14]	LI S, SHAN S, and CHEN X. Relative forest for attribute prediction[C]. Asian Conference on Computer Vision, Daejeon, Korea, 2012: 316-327.
[15]	JAYARAMAN D and GRAUMAN K. Zero shot recognition with unreliable attributes[C]. Conference on Neural Information Processing Systems, Montreal, QC, Canada, 2014: 3464-3472.
[16]	HUANG S, ELHOSEINY M, ELGAMMAL A, et al.. Learning hypergraph-regularized attribute predictors[C]. IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 2015: 409-417.
[17]	XUE J H and HALL P. Why does rebalancing class-unbalanced data improve AUC for linear discriminant analysis?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(5): 1109-12. doi: 10.1109/ TPAMI.2014.2359660.