Abstract
With multimedia databases it is difficult to specify queries directly and explicitly. Relevance feedback interactively learns a user’s desired output or query concept by asking the user whether certain proposed multimedia objects (e.g., images, videos, and songs) are relevant or not. For a learning algorithm to be effective, it must learn a user’s query concept accurately and quickly, while also asking the user to label only a small number of data instances. In addition, the concept-learning algorithm should consider the complexity of a concept in determining its learning strategies. This chapter\(^\dagger\) presents the use of support vector machines active learning in a concept-dependent way (\(\hbox{SVM}^{\rm CD}_{\rm Active}\) for conducting relevance feedback. A concept’s complexity is characterized using three measures: hit-rate, isolation and diversity. To reduce concept complexity so as to improve concept learnability, a multimodal learning approach is designed to use the semantic labels of data instances to intelligently adjust the sampling strategy and the sampling pool of \(\hbox{SVM}^{\rm CD}_{\rm Active}.\) Empirical study on several datasets shows that active learning outperforms traditional passive learning, and concept-dependent learning is superior to concept-independent relevance-feedback schemes.
†© ACM, 2004. This chapter is written based on the author’s work with Simon Tong [1], Kingshy Goh, and Wei-Cheng Lai [2]. Permission to publish this chapter is granted under copyright licenses #2587600971756 and #2587601214143.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The input space (denoted as X in machine learning and statistics literature) is defined as the original space in which the data vectors are located, and the feature space (denoted as F ) is the space into which the data are projected, either linearly or non-linearly.
- 2.
Query expansion is a vital component of any retrieval systems and it remains a challenging research area. This component is not deployed in our system yet and is part of our ongoing research.
- 3.
Unlike some recently developed systems [23] that contain a semantic layer between image features and queries to assist query refinement, our system does not have an explicit semantic layer. We argue that having a hard-coded semantic layer can make a retrieval system restrictive. Rather, dynamically learning the semantics of a query concept is more flexible and hence makes the system more useful.
- 4.
A query such as “animals”, “women”, and “European architecture” does not reside contiguously in the space formed by the image features.
References
S. Tong, E. Chang, Support vector machine active learning for image retrieval, in Proceedings of the ACM international conference on Multimedia, pp. 107–118 (2001)
K.S. Goh, E.Y. Chang, W.C. Lai, Multimodal concept-dependent active learning for image retrieval, in Proceedings of the ACM international conference on Multimedia, pp. 564–571 (2004)
D. Lewis, W. Gale, A sequential algorithm for training text classifiers, in Proceedings of the Seventeenth Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval (Springer, Heidelberg, 1994), pp. 3–12
A. McCallum, K. Nigam, Employing EM in pool-based active learning for text classification, In Proceedings of the Fifteenth International Conference on Machine Learning (Morgan Kaufmann, San Francisco, 1998), pp. 350–358
C. Burges, A tutorial on support vector machines for pattern recognition, in Proceedings of ACM KDD, pp. 121–167 (1998)
V. Vapnik, Estimation of Dependences Based on Empirical Data (Springer, Heidelberg, 1982)
C. Campbell, N. Cristianini, A. Smola, Query learning with large margin classifiers, in Proceedings of the Seventeenth International Conference on Machine Learning, pp. 111–118 (2000)
G. Schohn, D. Cohn, Less is more: active learning with support vector machines, in Proceedings of the Seventeenth International Conference on Machine Learning, pp. 839–846 (2000)
S. Tong, D. Koller, Support vector machine active learning with applications to text classification, in Proceedings of the 17th International Conference on Machine Learning, pp. 401–412 (June 2000)
M. Mendel, G. Poliner, D. Ellis, Support vector machine active learning for music retrieval. Multime’d. Syst. 12(1), 3–13 (2006)
T. Mitchell, Generalization as search. Artif. Intel. 28, 203–226 (1982)
J. Shawe-Taylor, N. Cristianini, Further results on the margin distribution, in Proceedings of the Twelfth Annual Conference on Computational Learning Theory, pp. 278–285 (1999)
V. Vapnik, Statistical Learning Theory (Wiley, NY, 1998)
R. Herbrich, T. Graepel, C. Campbell, Bayes point machines: estimating the bayes point in kernel space, in International Joint Conference on Artificial IntelligenceWorkshop on Support Vector Machines, pp. 23–27 (1999)
K. Brinker, Incorporating diversity in active learning with support vector machines, in Proceedings of the Twentieth International Conference on Machine Learning (ICML), pp. 59–66 (August 2003)
N. Roy, A. McCallum, Toward optimal active learning through sampling estimation of error reduction, in Proceedings of the Eighteenth International Conference on Machine Learning (ICML), pp. 441–448 (August 2001)
W.C. Lai, K. Goh, E.Y. Chang, On scalability of active learning for formulating query concepts, in Proceedings of Workshop on Computer Vision Meets Databases (CVDB) in cooperation with ACM International Conference on Management of Data (SIGMOD), pp. 11–18 (2004)
R. Agrawal, Fast algorithms for mining association rules in large databases, in Proceedings of VLDB, pp. 487–499 (1994)
R. Duda, P. Hart, D.G. Stork, Pattern Classification. 2nd edn. (Wiley, New York, 2001)
C. Li, E. Chang, H. Garcia-Molina, G. Wilderhold, Clindex: Approximate similarity queries in high-dimensional spaces.. IEEE Trans. Knowl. Data Eng. (TKDE) 14(4), 792–808 (2002)
E. Chang, B. Li, MEGA: the maximizing expected generalization algorithm for learning complex query concepts. ACM Trans. Inf. Syst. 21(4), 347–382 (2003)
E. Chang, K. Goh, G. Sychay, G. Wu, Content-based soft annotation for multimodal image retrieval using bayes point machines. IEEE Trans. Circuits. Syst. Video Technol. Special Issue Concept. Dynamical Aspects Multime’d. Content Descr. 13(1), 26–38 (2003)
J. Wang, J. Li, G. Wiederhold, Simplicity: semantics-sensitive integrated matching for picture libraries, in Proceedings of ACM Multimedia Conference, pp. 483–484 (2000)
C. Bishop, Neural Networks for Pattern Recognition (Oxford University Press, Oxford, 1998)
M. Kearns, U. Vazirani, An Introduction to Computational Learning Theory (MIT Press, USA, 1994)
T.M. Mitchell, Machine Learning (McGraw-Hill, NY, 1997)
X.S. Zhou, T.S. Huang, Comparing discriminating transformations and svm for learning during multimedia retrieval, in Proceedings of ACM Conference on Multimedia, pp. 137–146 (2001)
X.S. Zhou, T.S. Huang, Relevance feedback for image retrieval: a comprehensive review. ACM Multime’d. Syst. J., Special Issue on CBIR 8, 536–544 (2003)
K.S. Jones, P.Willett (eds.), Readings in Information Retrieval (Morgan Kaufman, San Francisco, July 1997)
K. Porkaew, K. Chakrabarti, S. Mehrotra, Query refinement for multimedia similarity retrieval in mars, in Proceedings of ACM International Conference on Multimedia, pp. 235–238 (1999)
L. Wu, C. Faloutsos, K. Sycara, T.R. Payne, Falcon: feedback adaptive loop for contentbased retrieval, in Proceedings of the 26th VLDB Conference, pp. 279–306 (September 2000)
M. Ortega-Binderberger, S. Mehrotra, Relevance feedback techniques in the MARS image retrieval system. Multime’d. Syst. 9(6), 535–547 (2004)
L. Breiman, Bagging predicators. Mach. Learn. 24(2), 123–140 (1996)
L. Breiman, Arcing classifiers. Ann. Statist. 26(3), 801–849 (1998)
A. Grove, D. Schuurmans, Boosting in the limit: maximizing the margin of learned ensembles, in Proceedings of 15th National Conference on Artificial Intelligence (AAAI), pp. 692–699 (1998)
R. Schapire, Y. Freund, P. Bartlett, W. Lee, Boosting the margin: a new explanation for the effectiveness of voting methods, in Proceeding of the Fourteenth International Conference on Machine Learning (Morgan Kaufmann, San Francisco, 1997) pp. 322–330
H. Wu, H. Lu, S. Ma, A practical svm-based algorithm for ordinal regression in image retri eval, in Proceedings of ACM International Conference on Multimedia, pp. 612–621 (2003)
T. Dietterich, G. Bakiri, Solving multiclass learning problems via error-correcting output codes. J. Artif. Intell. Res. 2, 263–286 (1995)
G. James, T. Hastie, Error coding and substitution PaCTs, in Proceedings of NIPS, (1997)
M. Moreira, E. Mayoraz, Improved pairwise coupling classification with error correcting classifiers, in Proceedings of ECML, pp. 160–171 (April 1998)
D. Cohn, Z. Ghahramani, M. Jordan, Active learning with statistical models. J. Artif. Intell. Res. 4, 129–145 (1996)
N. Cesa-Bianchi, Y. Freund, D. Haussler, D.P. Helmbold, R.E. Schapire, M.K. Warmuth, How to use expert advice. J. ACM 44(3), 427–485 (1997)
T. Jaakkola, H. Siegelmann, Active information retrieval, in Proceedings of NIPS, pp. 777–784 (2001)
S. Tong, E. Chang, Support vector machine active learning for image retrieval, in Proceedings of ACM International Conference on Multimedia, pp. 107–118 (October 2001)
Y. Freund, H. Seung, E. Shamir, N. Tishby, Selective sampling using the query by committee algorithm. Mach. Learn. 28, 133–168 (1997)
H. Seung, M. Opper, H. Sompolinsky, Query by committee, in Proceedings of the Fifth Workshop on Computational Learning Theory, (Morgan Kaufmann, San Francisco, 1992), pp. 287–294
I. Dagan, S. Engelson, Committee-based sampling for training probabilistic classifiers, in Proceedings of the Twelfth International Conference on Machine Learning (Morgan Kaufmann, San Francisco, 1995) pp. 150–157
T. Joachims, Text categorization with support vector machines, in Proceedings of ECML, (Springer, Heidelberg, 1998) pp. 137–142
S.T. Dumais, J. Platt, D. Heckerman, M. Sahami, Inductive learning algorithms and representations for text categorization, in Proceedings of the Seventh International Conference on Information and Knowledge Management, (ACM Press, NY, 1998) pp. 148–155
I.J. Cox, M.L. Miller, S.M. Omohundo, P.N. Yianilos, Pichunter: Bayesian relevance feedback for image retrieval, in Proceedings of International Conference on Pattern Recognition, pp. 361–369 (August 1996)
I.J. Cox, M.L. Miller, T.P. Minka, T.V. Papathomas, P.N. Yianilos, The Bayesian image retrieval system, Pichunter: theory, implementation and psychological experiments. IEEE Trans. Image Process. 9(1), 20–37 (2000)
E.Y. Chang, B. Li, G. Wu, K.S. Goh, Statistical learning for effective visual information retrieval (invited paper), in Proceedings of IEEE International Conference on Image Processing (ICIP), pp. 609–612 (2003)
J.J. Rocchio, Relevance feedback in information retrieval, in The SMART Retrieval System—Experiments in Automatic Document Processing, ed. by G. Salton (Prentice Hall, NJ, 1971) pp. 313–323
Y. Ishikawa, R. Subramanya, C. Faloutsos, Mindreader: querying databases through multiple examples, in Proceedings of VLDB, pp. 218–227 (1998)
M. Ortega, Y. Rui, K. Chakrabarti, A. Warshavsky, S. Mehrotra, T.S. Huang, Supporting ranked boolean similarity queries in mars. IEEE Trans. Knowl. Data Eng. 10(6), 905–925 (1999)
M. Ortega, Y. Rui, K. Chakrabarti, S. Mehrotra, T.S. Huang, Supporting similarity queries in mars, in Proceedings of ACM International Conference on Multimedia, pp. 403–413 (1997)
Y. Rui, T.S. Huang, M. Ortega, S. Mehrotra, Relevance feedback: A power tool in interactive content-based image retrieval. IEEE Trans. Circuits Syst. Video Technol. 8(5), 644–655 (1998)
K. Porkaew, S. Mehrota, M. Ortega, Query reformulation for content based multimedia retrieval in mars, in Proceedings of ICMCS, pp. 747–751 (1999)
M. Flickner, H. Sawhney, J. Ashley, Q. Huang, B. Dom, M. Gorkani, J. Hafner, D. Lee, D. Petkovic, D. Steele, P. Yanker, Query by image and video content: the QBIC system. IEEE Comput. 28(9), 23–32 (1995)
A. Gupta, R. Jain, Visual information retrieval. Commun. ACM 40(5), 69–79 (1997)
K.A. Hua, K. Vu, J.H. Oh, Sammatch: a flexible and efficient sampling-based image retrieval technique for image databases, in Proceedings of ACM Multimedia, pp. 225–234 (1999)
B.S. Manjunath, W.Y. Ma, Texture features for browsing and retrieval of image data. IEEE Trans. Pattern Anal. Mach. Intell. 18(8), 837–842 (1996)
J.R. Smith, S.F. Chang, VisualSEEk: a fully automated content-based image query system, in Proceedings of ACM Multimedia, pp. 87–98 (1996)
J.Z. Wang, G. Wiederhold, O. Firschein, S.X. Wei, Wavelet-based image indexing techniques with partial sketch retrieval capability, in Proceedings of the ADL, pp. 13–24 (May 1997)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg and Tsinghua University Pres
About this chapter
Cite this chapter
Chang, E.Y. (2011). Query Concept Learning. In: Foundations of Large-Scale Multimedia Information Management and Retrieval. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-20429-6_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-20429-6_3
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-20428-9
Online ISBN: 978-3-642-20429-6
eBook Packages: Computer ScienceComputer Science (R0)