|本期目录/Table of Contents|

[1]冀中,谢于中,庞彦伟.基于典型相关分析和距离度量学习的零样本学习[J].天津大学学报(自然科学版),2017,(08):813-820.[doi:10.11784/tdxbz201606003]
 Ji Zhong,Xie Yuzhong,Pang Yanwei.Zero-Shot Learning Based on Canonical Correlation Analysis and Distance Metric Learning[J].Journal of Tianjin University,2017,(08):813-820.[doi:10.11784/tdxbz201606003]
点击复制

基于典型相关分析和距离度量学习的零样本学习()
分享到:

《天津大学学报(自然科学版)》[ISSN:0493-2137/CN:12-1127/N]

卷:
期数:
2017年08
页码:
813-820
栏目:
电气自动化与信息工程
出版日期:
2017-08-31

文章信息/Info

Title:
Zero-Shot Learning Based on Canonical Correlation Analysis and Distance Metric Learning
文章编号:
0493-2137(2017)08-0813-08
作者:
冀中 谢于中 庞彦伟
天津大学电气自动化与信息工程学院,天津 300072
Author(s):
Ji Zhong Xie Yuzhong Pang Yanwei
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
关键词:
零样本学习 典型相关分析 距离度量学习 图像分类
Keywords:
zero-shot learning canonical correlation analysis distance metric learning image classification
分类号:
TP391.41
DOI:
10.11784/tdxbz201606003
文献标志码:
A
摘要:
零样本学习是一类特殊的图像分类问题, 是指测试数据的类别在训练数据中没有出现的情况.为了更好地描述语义特征空间中图像特征和语义特征的距离关系, 本文将距离度量学习引入零样本学习任务.具体而言, 首先利用典型相关分析将样本的图像特征和相应类别的语义特征映射至公共特征空间; 然后, 利用距离度量学习衡量图像特征和语义特征之间的距离; 最后, 使用最近邻分类器进行分类.通过在流行的AwA和CUB数据集中的实验, 证明了所提方法的有效性和鲁棒性.
Abstract:
Zero-shot learning is a special case of image classification,whose test classes are absent in training samples. To better measure the distance between visual features and semantic features in the semantic embedding space,a distance metric learning based zero-shot learning method is proposed. Specifically,visual features and semantic features were first projected into a common semantic embedding space by use of canonical correlation analysis,then a distance metric learning method was employed to measure the distance between them. Finally,a nearest neighbor classifier was utilized to perform the classification. Experimental results on the popular AwA and CUB datasets demonstrate that the proposed approach is effective and robust.

参考文献/References:

[1] Socher R, Ganjoo M, Manning C D, et al. Zero-shot learning through cross-modal transfer[C]//Advances in Neural Information Processing Systems. Lake Tahoe, USA, 2013:935-943.
[2] Frome A, Corrado G S, Shlens J, et al. Devise:A deep visual-semantic embedding model[C]//Advances in Neural Information Processing Systems. Lake Tahoe, USA, 2013:2121-2129.
[3] Pimentel M A F, Clifton D A, Clifton L, et al. A review of novelty detection[J]. Signal Processing, 2014, 99(6):215-249.
[4] Deng C, Tang X, Yan J, et al. Discriminative dictionary learning with common label alignment for cross-modal retrieval[J]. IEEE Transactions on Multimedia, 2016, 18(2):208-218.
[5] Liu X, Deng C, Lang B, et al. Query-adaptive reciprocal hash tables for nearest neighbor search[J]. IEEE Transactions on Image Processing, 2016, 25(2):907-919.
[6] Deng C, Ji R, Tao D, et al. Weakly supervised multi-graph learning for robust image reranking[J]. IEEE Transactions on Multimedia, 2014, 16(3):785-795.
[7] Yang Y, Deng C, Tao D, et al. Latent max-margin multitask learning with skelets for 3-D action recognition [J]. IEEE Transactions on Cybernetics, 2016:1-10.
[8] Hotelling H. Relations between two sets of variates[J]. Biometrika, 1936, 28(3/4):321-377.
[9] Rasiwasia N, Costa Pereira J, Coviello E, et al. A new approach to cross-modal multimedia retrieval[C]// ACM International Conference on Multimedia. Firenze, Italy, 2010:251-260.
[10] Zhang H, Zhuang Y, Wu F. Cross-modal correlation learning for clustering on image-audio dataset[C]// ACM International Conference on Multimedia. Augsburg, Germany, 2007:273-276.
[11] Hardoon D R, Szedmak S, Shawe-Taylor J. Canonical correlation analysis:An overview with application to learning methods[J]. Neural Computation. 2004, 16(12):2639-2664.
[12] Fu Z, Xiang T, Kodirov E, et al. Zero-shot object recognition by semantic manifold distance[C]// IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA, 2015:2635-2644.
[13] Lampert C H, Nickisch H, Harmeling S. Attribute-based classification for zero-shot visual object categorization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(3):453-465.
[14] Romera-Paredes B, Torr P H S. An embarrassingly simple approach to zero-shot learning[C]//Proceedings of The 32nd International Conference on Machine Learning. Lille, France, 2015:2152-2161.
[15] Liu M, Zhang D, Chen S. Attribute relation learning for zero-shot classification[J]. Neurocomputing, 2014, 139:34-46.
[16] 巩萍, 程玉虎, 王雪松. 基于属性关系图正则化特征选择的零样本分类[J]. 中国矿业大学学报, 2015, 44(6):1097-1104.
Gong Ping, Cheng Yuhu, Wang Xuesong. Zero-shot classification based on attribute correlation graph regularized feature selection[J]. Journal of China University of Mining and Technology, 2015, 44(6):1097-1104(in Chinese).
[17] Mikolov T, Sutskever I, Chen K, et al. Distributed representations of words and phrases and their compositionality[C]//Advances in Neural Information Processing Systems. Lake Tahoe, USA, 2013:3111-3119.
[18] Pennington J, Socher R, Manning C D. Glove:Global vectors for word representation[C]//Conference on Empirical Methods on Natural Language Processing. Doha, Qatar, 2014:1532-1543.
[19] Akata Z, Reed S, Walter D, et al. Evaluation of output embeddings for fine-grained image classification[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA, 2015:2927-2936.
[20] Xian Y, Akata Z, Sharma G, et al. Latent embeddings for zero-shot classification[C]// IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016:69-77.
[21] Xing E P, Ng A Y, Jordan M I, et al. Distance metric learning with application to clustering with side-information[C]//Advances in Neural Information Processing Systems. Vancouver, Canada, 2003:521-528.
[22] Wah C, Branson S, Welinder P, et al. The caltech-ucsd birds-200-2011 dataset[EB/OL]. http://www.vision. caltech.edu/visipedia/CUB-200-2011.html, 2011-01-15.
[23] Zhang Z, Saligrama V. Zero-shot learning via semantic similarity embedding[C]// IEEE International Conference on Computer Vision. Santiago, Chile, 2015:4166-4174.
[24] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C] // International Conference on Learning Representations. San Diego, USA, 2015:1-13.

相似文献/References:

[1]冀中,郭威辰.基于局部保持典型相关分析的零样本动作识别[J].天津大学学报(自然科学版),2017,(09):975.[doi:10.11784/tdxbz201607010]
 Ji Zhong,Guo Weichen.Zero Shot Action Recognition Based on Local Preserving Canonical Correlation Analysis[J].Journal of Tianjin University,2017,(08):975.[doi:10.11784/tdxbz201607010]

备注/Memo

备注/Memo:
收稿日期: 2016-06-03; 修回日期: 2016-11-24.
作者简介: 冀中(1979—), 男, 博士, 副教授.
通讯作者: 冀中, jizhong@tju.edu.cn.
基金项目: 国家自然科学基金资助项目(61472273, 61632018).
Supported by the National Natural Science Foundation of China(Nos. 61472273 and 61632018).
更新日期/Last Update: 2017-08-10