Nonlinear distance function learning using neural network: an iterative framework

详细信息    查看全文

• 作者：Junying Chen (1)
  Haoyu Zeng (1)
  Na Fan (2)
  
  1. College of Sciences ; Agricultural University of Hebei ; 289 Lingyu Temple St. ; Baoding ; Hebei ; 071001 ; China
  2. Department of Electronic Engineering ; East China Normal University ; 500 Dongchuan Rd ; Shanghai ; 200241 ; People鈥檚 Republic of China
  
• 关键词：Metric learning ; Multimodal learning ; Nonlinearity ; Regression models
• 刊名：Multimedia Tools and Applications
• 出版年：2015
• 出版时间：February 2015
• 年：2015
• 卷：74
• 期：3
• 页码：671-688
• 全文大小：1,655 KB
• 参考文献：1. Balasubramanian VN, Ye J, Panchanathan S (2007) Biased manifold embedding: A framework for person-independent head pose estimation, Proc. CVPR, pp.1鈥?
  2. Bar-Hillel AD (2007) Weinshall, Learning distance function by coding similarity, Proc. ICML, pp.65鈥?2
  3. Castillo E, Berdinas BG, Romero OF, Betanzos AA (2006) A very fast learning method for neural networks based on sensitivity analysis. J Mach Learn Res 7:1159鈥?182
  4. Cherkassky V, Shao X, Mulier FM, Vapnik VN (1999) Model complexity control for regression using VC generalization bounds. IEEE Trans Neural Netw 10(5):1075鈥?089 CrossRef
  5. Chopra S, Hadsell R, LeCun Y (2005) Learning a similarity metric discriminatively, with application to face verification, Proc. CVPR, pp.539鈥?46
  6. Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans on PAMI 23(6):681鈥?85 CrossRef
  7. Davis JV, Kulis B, Jain P, Sra V, Dhillon IS (2007) Information-theoretic metric learning, Proc. ICML, pp.209鈥?16
  8. Fan N (2011) Learning nonlinear distance functions using neural network for regression with application to robust human age estimation, Proc. ICCV, pp.249鈥?54
  9. FG-NET Aging Database, http://www.fgnet.rsunit.com
  10. Geng X, Miles KS, Zhou ZZ (2008) Facial age estimation by nonlinear aging pattern subspace, Proc. ACM Multimedia, pp.721鈥?24
  11. Geng X, Zhou ZH, Miles KS (2007) Automatic age estimation based on facial aging patterns. IEEE Trans PAMI 29(12)):2234鈥?240 CrossRef
  12. Goldberger J, Roweis S, Hinton G, Salakhutdinov R (2005) Neighbourhood components analysis, Proc. NIPS, pp.513鈥?20
  13. Guo GD, Mu G, Fu Y, Dyer C, Huang TS (2009) A study on automatic age estimation using a large database, Proc. ICCV, pp.1鈥?
  14. Guo GD, Mu G, Fu Y, Huang (2009) Human age estimation using bio-inspired features, Proc. CVPR, pp.1鈥?
  15. He X, Ma WY, Zhang HJ (2004) Learning an image manifold for retrieval, Proc. ACM Multimedia, pp.17鈥?3
  16. Huang YZ, Long YJ (2008) Demosaicking recognition with applications in digital photo authentication based on a quadratic pixel correlation model, Proceedings of CVPR, pp.1鈥?
  17. Jin C, Long YJ (2010) On label information incorporated metric learning for regressions. Int J Comput Intell Appl 9(4):339鈥?51 CrossRef
  18. Lanitis A, Draganova C, Christodoulou C (2004) Comparing different classifiers for automatic age estimation. IEEE Trans SMC-B 34(1):621鈥?28
  19. Long YJ, Huang YZ (2006) Image based source camera identification using demosaicking, Proceedings of the 8th International conference on Workshop Multimedia Signal Processing, pp. 419鈥?24
  20. Macskassy SA, Hirsh H, Banerjee A, Dayanik AA (2003) Converting numerical classification into text classification. Artif Intell 143(1):51鈥?7 CrossRef
  21. McCullagh P (1980) Regression models for ordinal data. J R Stat Soc Ser B 42(2):109鈥?42
  22. Min R, van der Maaten LJP, Yuan Z, Bonner A, Zhang Z (2010) Deep supervised t-distributed embedding, Proc. ICML, pp.791鈥?98
  23. Moller AF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6(4):525鈥?33 CrossRef
  24. Pan (2010) Human age estimation by metric learning for regression problems. Proc. EMM CVPR, pp. 455鈥?65
  25. Ramanathan N, Chellappa R, Biswas S (2009) Age progression in human faces: a survey. J Vis Lang Comput 20:131鈥?44 CrossRef
  26. Salakhutdinov R, Hinton G (2007) Learning a nonlinear embedding by preserving class neighbourhood structure, Proc. AI and Statistics, pp. 412鈥?19
  27. Shalev-Shwartz S, Singer Y, Ng AY (2004) Online and batch learning of pseudo-metrics, Proc. ICML, pp.743鈥?50
  28. Shental N, Hertz T, Weinshall D, Pavel M (2002) Adjustment learning and relevant component analysis, Proc. ECCV, pp.776鈥?92
  29. Smith L (2002) A tutorial on Principal Components Analysis http://www.cs.otago.ac.nz/cosc453/student_tutorials/principal_components.pdf
  30. Stanley KO (2007) Compositional pattern producing networks: a novel abstraction of development. Genet Program Evolvable Mach 8(2):131鈥?62 CrossRef
  31. Tan X, Chen S, Li J, Zhou Z (2006) Learning non-metric partial similarity based on maximal margin criterion, Proc. CVPR, pp.138鈥?45
  32. Taylor G, Fergus R, Williams G, Spiro I, Bregler C (2010) Pose-sensitive embedding by nonlinear NCA regression. Proc, NIPS
  33. Weinberger K, Blitzer J, Saul L (2006) Distance metric learning for large margin nearest neighbor classification, Proc. NIPS, pp.1475鈥?482
  34. Xing E, Ng A, Jordan MI, Russell S (2002) Distance metric learning with application to clustering with side-information, Proc. NIPS, pp.505鈥?12
  35. Yan S, Wang H, Huang TS, Tang X (2007) Ranking with uncertain labels, Proc. ICME, pp.96鈥?9
  36. Yan S, Wang H, Tang X, Huang T (2007) Learning auto-structured regressor from uncertain nonnegative labels. Proc. ICCV, pp.1鈥?
  37. Yan S, Zhou X, M. Liu, M. H. Johnson, T. Huang (2008) Regression from patch-kernel, Proc. CVPR, pp.1鈥?
  38. Yang L, Jin R (2006) Distance metric learning: a comprehensive survey, Technical report, Michigan State University. http://www.cs.cmu.edu/~liuy/frame_survey_v2.pdf
  39. Yeung DY, Chang H (2007) A kernel approach for semi-supervised metric learning. IEEE Trans on Neural Net 18(1):141鈥?49 CrossRef
  
• 刊物类别：Computer Science
• 刊物主题：Multimedia Information Systems
  Computer Communication Networks
  Data Structures, Cryptology and Information Theory
  Special Purpose and Application-Based Systems
  
• 出版者：Springer Netherlands
• ISSN：1573-7721

文摘

In this paper, we extend several existing methods that apply distance function learning to regression problems. We discover that these methods may be viewed as approximating a matrix consisting of desired distances among all training samples. Based on this understanding, we propose an iterative framework where outlier samples are corrected by their neighbors via asymptotically increasing the correlation coefficients between the desired distances and the distances of sample labels. Moreover, using this framework, we find that most existing methods iterate only once. As another extension, we adopt a nonlinear distance function and approximate it with neural network. For a fair comparison, we conduct an experiment on age estimation from face images as a regression problem, and the results are comparable to the state of the art.