图像检索中结合文本信息的多示例原型选择及主动学习策略

doi:10.3724/SP.J.1087.2012.02899

计算机应用 ›› 2012, Vol. 32 ›› Issue (10): 2899-2903.DOI: 10.3724/SP.J.1087.2012.02899

图像检索中结合文本信息的多示例原型选择及主动学习策略

李净¹,²,郭洪禹¹

1. 上海海洋大学信息学院,上海 201306
2. 同济大学电子与信息工程学院,上海 201804

收稿日期:2012-04-17 修回日期:2012-05-20 发布日期:2012-10-23 出版日期:2012-10-01
通讯作者: 李净
作者简介:李净(1977-),女,山西阳泉人,副教授,博士,主要研究方向：图像检索、机器学习；郭洪禹(1974-),女,黑龙江齐齐哈尔人,讲师,博士研究生,主要研究方向：模式识别、语音处理。
基金资助:
国家863计划项目

Multi-instance prototype selection and active learning combined with textual information in image retrieval

LI Jing¹,²,GUO Hong-yu¹

1. College of Information Technology, Shanghai Ocean University,Shanghai 201306, China
2. School of Electronics and Information, Tongji University, Shanghai 201804, China

Received:2012-04-17 Revised:2012-05-20 Online:2012-10-23 Published:2012-10-01
Contact: LI Jing

摘要/Abstract

摘要： 针对基于区域的图像检索系统检索精度不高的问题,提出结合文本信息的多示例原型选择算法和反馈标注机制。在示例原型选择时,首先使用文本信息进行正例拓展,然后通过估计负示例分布进行最初示例选择,最后通过示例更新和分类器学习的交替优化获得真的示例原型。相关反馈采用了多策略相结合的主动学习机制,通过信息值控制主动学习策略的自动切换,使系统能够自动选择当前最适合的主动学习策略。实验结果表明,该方法有效且性能优于其他方法。

关键词: 多示例学习, 文本信息, 示例原型, 主动学习, 相关反馈

Abstract: For the poor precision of region-based image retrieval, Multi-Instance Learning (MIL) prototype selection algorithm and feedback mechanism with reference to textual information were proposed. In the process of instance prototype selection, textual information was used to extend the positive examples, and negative example distribution was used to select initial instances and the iterative optimization process of instance updating and classifier training were used to obtain the true instance prototypes. In the process of relevance feedback, active learning with the combined learning methods was adopted. The switch of active learning strategy was controlled by the information value in the feedback process. The experimental results show that this algorithm is feasible, and the performance is superior to other MIL algorithms.

Key words: Multi-Instance Learning (MIL), textural information, instance prototype, active learning, relevance feedback

李净郭洪禹. 图像检索中结合文本信息的多示例原型选择及主动学习策略[J]. 计算机应用, 2012, 32(10): 2899-2903.

LI Jing GUO Hong-yu. Multi-instance prototype selection and active learning combined with textual information in image retrieval[J]. Journal of Computer Applications, 2012, 32(10): 2899-2903.

参考文献

［1］ RAHMANI R, GOLDMAN S A, ZHANG H. Localized content based image retrieval[C]// MIR05: Proceedings of the 7th ACM SIGMM International Workshop on Multimedia Information Retrieval.New York: ACM, 2005:227-236. ［2］ ZHANG Q, GOLDMAN S A, YU W, et al. Content-based image retrieval using multiple-instance learning[C]// ICML02: Proceedings of the Nineteenth International Conference on Machine Learning. San Francisco:Morgan Kaufmann Publishers Inc.,2002:682-689. ［3］ BUNESCU R C, MOONEY R J. Multiple instance learning for sparse positive bags[C]// ICML07: Proceedings of the 24th International Conference on Machine Learning. New York:ACM,2007:105-112. ［4］ YANG C, DONG M, HUA J. Region-based image annotation using asymmetrical support vector machine-based multiple instance learning[C]// CVPR06: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington, DC: IEEE Computer Society, 2006,2:2057-2063. ［5］ CHEN Y, WANG J Z. Image categorization by learning and reasoning with regions[J]. Journal of Machine Learning Research, 2004,12(5): 913-939. ［6］ CHEN Y, BI J, WANG J Z. MILES: Multiple-instance learning via embedded instance selection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006,28(12):1931-1947. ［7］ LI W-J, YEUNG D Y. Localized content-based image retrieval through evidence region identification[C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington,DC:IEEE, 2009:1666-1673. ［8］ FU Z, ROBLES-KELLY A, ZHOU J. MILIS: multiple instance learning with instance selection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011,33(5):958-77. ［9］ ZHANG D, WANG F, SHI Z, et al.Interactive localized content based image retrieval with multiple-instance active learning［J］. Pattern Recognition, 2010,43(2):478-484. ［10］ SETTLES B, CRAVEN M, RAY S. Multiple instance active learning［EB/OL］.[2012-01-01].http://www.books.nips.cc/papers/files/nips20/NIPS2007_1072.pdf. ［11］ LIU DONG, HUA XIAN-SHENG, YANG LIN-JUN, et al.Multiple-instance active learning for image categorization[C]// MMM09: Proceedings of the 15th International Multimedia Modeling Conference on Advances in Multimedia Modeling. Berlin: Springer-Verlag, 2009:239-249. ［12］ ARYA S, MOUNT D M, NETANYAHU N S, et al. An optimal algorithm for approximate nearest neighbor searching fixed dimensions［J］. Journal of the ACM, 1998,45(6):891-923. ［13］ DUDA R O, HART P E, STORK D G. Pattern Classification［M］. 2nd ed. New York: John Wiley and Sons,2001. ［14］ TANG HANGHANG, HE JINGRUI, LI MINGJING, et al. Manifold-ranking-based keyword propagation for image retrieval［J］. Journal on Applied Signal Processing, 2006,2006(1):1-10.

[1]	易东义, 邓根强, 董超雄, 祝苗苗, 吕周平, 朱岁松. 基于图卷积神经网络的医保欺诈检测算法[J]. 计算机应用, 2020, 40(5): 1272-1277.
[2]	汪敏, 武禹伯, 闵帆. 基于多种聚类算法和多元线性回归的多分类主动学习算法[J]. 计算机应用, 2020, 40(12): 3437-3444.
[3]	任杰, 闵帆, 汪敏. 基于最远总距离采样的代价敏感主动学习[J]. 计算机应用, 2019, 39(9): 2499-2504.
[4]	龚彦鹭, 吕佳. 结合主动学习和密度峰值聚类的协同训练算法[J]. 计算机应用, 2019, 39(8): 2297-2301.
[5]	邱宁佳, 丛琳, 周思丞, 王鹏, 李岩芳. 结合改进主动学习的SVD-CNN弹幕文本分类算法[J]. 计算机应用, 2019, 39(3): 644-650.
[6]	柴变芳, 吕峰, 李文斌, 王垚. 基于主动学习先验的半监督K-means聚类算法[J]. 计算机应用, 2018, 38(11): 3139-3143.
[7]	翟俊海, 张素芳, 王聪, 沈矗, 刘晓萌. 基于MapReduce的大数据主动学习[J]. 计算机应用, 2018, 38(10): 2759-2763.
[8]	王莉莉, 付忠良, 陶攀, 朱锴. 基于多分类AdaBoost改进算法的TEE标准切面分类[J]. 计算机应用, 2017, 37(8): 2253-2257.
[9]	王莉莉, 付忠良, 陶攀, 胡鑫. 基于主动学习不平衡多分类AdaBoost算法的心脏病分类[J]. 计算机应用, 2017, 37(7): 1994-1998.
[10]	张良, 罗祎敏, 马洪超, 张帆, 胡川. 基于未标签信息主动学习算法的高光谱影像分类[J]. 计算机应用, 2017, 37(6): 1768-1771.
[11]	朱江, 明月, 王森. 基于深度自编码网络的安全态势要素获取机制[J]. 计算机应用, 2017, 37(3): 771-776.
[12]	柴变芳, 王建岭, 许冀伟, 李文斌. 基于链接模型的主动半监督社区发现方法[J]. 计算机应用, 2017, 37(11): 3090-3094.
[13]	闫蓉, 高光来. 基于检索结果排序的伪相关反馈[J]. 计算机应用, 2016, 36(8): 2099-2102.
[14]	白晓红, 温静, 赵雪, 陈金广. 基于加速鲁棒特征和多示例学习的目标跟踪算法[J]. 计算机应用, 2016, 36(11): 2974-2978.
[15]	李艳玲, 颜永红. 中文口语理解弱监督训练方法[J]. 计算机应用, 2015, 35(7): 1965-1968.

图像检索中结合文本信息的多示例原型选择及主动学习策略

Multi-instance prototype selection and active learning combined with textual information in image retrieval

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics