JOINT PROBABILITY ESTIMATION OF ATTRIBUTE CHAIN FOR ZERO-SHOT LEARNING

被引：0

作者：

Qiao, Lingfeng ^{[1
]}

Tuo, Hongya ^{[1
]}

Fang, Zheng ^{[1
]}

Feng, Peng ^{[1
]}

Jing, Zhongliang ^{[1
]}

机构：

[1] Shanghai Jiao Tong Univ, Sch Aeronaut & Astronaut, Shanghai 200240, Peoples R China

来源：

2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2016年

关键词：

Zero-shot learning; attribute relation; joint probability; classifier chain;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Zero-shot learning (ZSL) aims to classify the objects without any training samples. Direct Attribute Prediction (DAP) gives a solution with attribute space but it makes the assumption of attribute independence. To relax this assumption and consider the relation among attributes, Joint Attribute Chain Prediction (JACP) algorithm is proposed in this paper. It estimates the joint probability of attribute chain by the multiplication formula without the independence assumption. To deal with the difficulty of estimation, clustering algorithm of attributes is presented to generate several independent attribute sets. Each set trains a series of classifiers to calculate the joint probability individually and then the posteriori of classes can be obtained. Experiments on AwA and aPascal-aYahoo data sets demonstrate the effectiveness of our algorithm.

引用

页码：1863 / 1867

页数：5

共 17 条

[1] Label-Embedding for Attribute-Based Classification [J].

Akata, Zeynep ;

Perronnin, Florent ;

Harchaoui, Zaid ;

Schmid, Cordelia .

2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, :819-826

[2]

Dembczynski K, 2010, P 2 INT WORKSH LEARN, P5

[3]

Dembczynski K., 2010, PROC INTCONF MACH LE, P279

[4]

Farhadi A, 2009, PROC CVPR IEEE, P1778, DOI 10.1109/CVPRW.2009.5206772

[5]

Fu YW, 2014, LECT NOTES COMPUT SC, V8690, P584, DOI 10.1007/978-3-319-10605-2_38

[6] PLSA-BASED ZERO-SHOT LEARNING [J].

Hoo, Wai Lam ;

Chan, Chee Seng .

2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013), 2013, :4297-4301

[7]

Kankuekul P, 2012, PROC CVPR IEEE, P3657, DOI 10.1109/CVPR.2012.6248112

[8] Attribute-Based Classification for Zero-Shot Visual Object Categorization [J].

Lampert, Christoph H. ;

Nickisch, Hannes ;

Harmeling, Stefan .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2014, 36 (03) :453-465

[9]

Lampert CH, 2009, PROC CVPR IEEE, P951, DOI 10.1109/CVPRW.2009.5206594

[10] BAP: Bimodal Attribute Prediction for Zero-Shot Image Categorization [J].

Li, Hanhui ;

Li, Donghui ;

Luo, Xiaonan .

PROCEEDINGS OF THE 2014 ACM CONFERENCE ON MULTIMEDIA (MM'14), 2014, :1013-1016

← 1 2 →