Skip to main content
SpringerLink
Log in

Large scale classifiers for visual classification tasks

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

ImageNet dataset with more than 14 million images and 21,000 classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate visual classifier on several multi-core computers with limited individual memory resource. In this paper we address this challenge by extending both state-of-the-art large scale linear classifier (LIBLINEAR-CDBLOCK) and non-linear classifier (Power Mean SVM) for large scale visual classification tasks in these following ways: (1) an incremental learning method for Power Mean SVM, (2) a balanced bagging algorithm for training binary classifiers. Our approach has been evaluated on the 100 largest classes of ImageNet and ILSVRC 2010. The evaluation shows that our approach can save up to 82.01 % memory usage and the learning process is much faster than the original implementation and LIBLINEAR SVM.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Berg A, Deng J, Li FF (2010) Large scale visual recognition challenge 2010. Tech rep. http://www.image-net.org/challenges/LSVRC/2010/index

  2. Chawla NV, Lazarevic A, Hall LO, Bowyer KW (2003) Smoteboost: improving prediction of the minority class in boosting. In: The principles of knowledge discovery in databases, pp 107–119

  3. Crammer K, Singer Y (2002) On the learnability and design of output codes for multiclass problems. Mach Learn 47(2–3):201–233

    Article  MATH  Google Scholar 

  4. Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, Cambridge

    Book  Google Scholar 

  5. Csurka G, Dance CR, Fan L, Willamowski J, Bray C (2004) Visual categorization with bags of keypoints. In: Workshop on statistical learning in computer vision, European conference on computer vision, pp 1–22

  6. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE computer society conference on computer vision and pattern recognition. IEEE Computer Society, pp 886–893

  7. Deng J, Berg AC, Li K, Li FF (2010) What does classifying more than 10,000 image categories tell us? In: European conference on computer vision, pp 71–84

  8. Deng J, Dong W, Socher R, Li LJ, Li K, Li FF (2009) Imagenet: a large-scale hierarchical image database. In: IEEE computer society conference on computer vision and pattern recognition, pp 248–255

  9. Do TN, Nguyen VH, Poulet F (2008) Speed up svm algorithm for massive classification tasks. In: International conference on advanced data mining and applications, pp 147–157

  10. Doan TN, Do TN, Poulet F (2013) Large scale visual classification with parallel, imbalanced bagging and incremental liblinear svm. In: 9th international conference on data mining. Las Vegas, Nevada, pp 197–203

  11. Doan TN, Do TN, Poulet F (2013) Parallel incremental svm for classifying million images with very high-dimensional signatures into thousand classes. In: IEEE international joint conference on neural networks. Dallas, pp 2976–2983

  12. Duda RO, Hart PE (1973) Pattern classification and scene analysis. Wiley, New York

    MATH  Google Scholar 

  13. Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303–338

    Article  Google Scholar 

  14. Fergus R, Weiss Y, Torralba A (2009) Semi-supervised learning in gigantic image collections. In: Advances in neural information processing systems, pp 522–530

  15. Griffin G, Holub A, Perona P (2007) Caltech-256 object category dataset. Tech. Rep. CNS-TR-2007-001, California Institute of Technology. http://authors.library.caltech.edu/7694

  16. Griffin G, Perona D (2008) Learning and using taxonomies for fast visual categorization. In: IEEE computer society conference on computer vision and pattern recognition. IEEE Computer Society

  17. Guermeur Y (2007) Svm multiclasses, théorie et applications

  18. Hsieh CJ, Chang KW, Lin CJ, Keerthi SS, Sundararajan S (2008) A dual coordinate descent method for large-scale linear svm. In: International conference on machine learning, pp 408–415

  19. Japkowicz N (ed) (2000) AAAI’Workshop on learning from imbalanced data sets, no. WS-00-05 in AAAI Tech Report

  20. Joachims T (2006) Training linear svms in linear time. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery. ACM, pp 217–226

  21. Keerthi SS, Sundararajan S, Chang KW, Hsieh CJ, Lin CJ (2008) A sequential dual method for large scale multi-class linear svms. In: KDD, pp 408–416

  22. Krebel U (1999) Pairwise classification and support vector machines. In: Advances in kernel methods: support vector learning, pp 255–268

  23. Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: IEEE computer society conference on computer vision and pattern recognition, pp 2169–2178

  24. Lenca P, Lallich S, Do TN, Pham NK (2008) A comparison of different off-centered entropies to deal with class imbalance for decision trees. In: The Pacific-Asia conference on knowledge discovery and data mining, LNAI 5012. Springer, pp 634–643

  25. Li FF, Fergus R, Perona P (2007) Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. Comput Vis Image Underst 106(1):59–70

    Article  Google Scholar 

  26. Li Y, Crandall DJ, Huttenlocher DP (2009) Landmark classification in large-scale image collections. In: IEEE 12th international conference on computer vision. IEEE, pp 1957–1964

  27. Lin CJ, Weng RC, Keerthi SS (2008) Trust region newton method for logistic regression. J Mach Learn Res 9:627–650

    MATH  MathSciNet  Google Scholar 

  28. Lin Y, Lv F, Zhu S, Yang M, Cour T, Yu K, Cao L, Huang TS (2011) Large-scale image classification: Fast feature extraction and svm training. In: IEEE computer society conference on computer vision and pattern recognition, pp 1689–1696

  29. Liu XY, Wu J, Zhou ZH (2009) Exploratory undersampling for class-imbalance learning. IEEE Trans Syst Man Cybern Part B 39(2):539–550

    Article  Google Scholar 

  30. Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110

    Article  Google Scholar 

  31. Maji S, Berg AC, Malik J (2008) Classification using intersection kernel support vector machines is efficient. In: IEEE computer society conference on computer vision and pattern recognition

  32. Maji S, Berg AC, Malik J (2013) Efficient classification for additive kernel svms. IEEE Trans Pattern Anal Mach Intell 35(1):66–77

    Article  Google Scholar 

  33. MPI-Forum: Mpi: a message-passing interface standard. http://www.mpi-forum.org

  34. OpenMP Architecture Review Board: OpenMP application program interface version 3.0. http://www.openmp.org/mp-documents/spec30.pdf (2008)

  35. Perronnin F, Akata Z, Harchaoui Z, Schmid C (2012) Towards good practice in large-scale learning for image classification. In: IEEE computer society conference on computer vision and pattern recognition, pp 3482–3489

  36. Perronnin F, Sánchez J, Liu Y (2010) Large-scale image categorization with explicit data embedding. In: IEEE computer society conference on computer vision and pattern recognition, pp 2297–2304

  37. Pham NK, Do TN, Lenca P, Lallich S (2008) Using local node information in decision trees: coupling a local decision rule with an off-centered entropy. In: International conference on data mining. CSREA Press, Las Vegas, pp 117–123

  38. Platt J, Cristianini N, Shawe-Taylor J (2000) Large margin dags for multiclass classification. Adv Neural Inf Process Syst 12:547–553

    Google Scholar 

  39. Ricamato MT, Marrocco C, Tortorella F (2008) Mcs-based balancing techniques for skewed classes: an empirical comparison. In: International conference on pattern recognition, pp 1–4

  40. Sánchez J, Perronnin F (2011) High-dimensional signature compression for large-scale image classification. In: IEEE computer society conference on computer vision and pattern recognition, pp 1665–1672

  41. Shalev-Shwartz S, Singer Y, Srebro N (2007) Pegasos: primal estimated sub-gradient solver for svm. In: International conference on machine learning, pp 807–814

  42. Suykens JAK, Vandewalle J (1999) Least squares support vector machine classifiers. Neural Process Lett 9(3):293–300. doi:10.1023/A:1018628609742

    Article  MathSciNet  Google Scholar 

  43. Vapnik V (1995) The nature of statistical learning theory. Springer, Berlin

    Book  MATH  Google Scholar 

  44. Vedaldi A, Gulshan V, Varma M, Zisserman A (2009) Multiple kernels for object detection. In: IEEE 12th international conference on computer vision. IEEE, pp 606–613

  45. Vedaldi A, Zisserman A (2012) Efficient additive kernels via explicit feature maps. IEEE Trans Pattern Anal Mach Intell 34(3):480–492

    Article  Google Scholar 

  46. Visa S, Ralescu A (2005) Issues in mining imbalanced data sets–a review paper. In: Midwest artificial intelligence and cognitive science conf. Dayton, pp 67–73

  47. Wang C, Yan S, Zhang HJ (2009) Large scale natural image classification by sparsity exploration. In: Proceedings of the IEEE international conference on acoustics, speech, and signal processing. IEEE, pp 3709–3712

  48. Weiss GM, Provost F (2003) Learning when training data are costly: the effect of class distribution on tree induction. J Artif Intell Res 19:315–354

    MATH  Google Scholar 

  49. Weston J, Watkins C (1999) Support vector machines for multi-class pattern recognition. In: Proceedings of the seventh European symposium on artificial neural networks, pp 219–224

  50. Wu J (2010) A fast dual method for hik svm learning. In: Daniilidis K, Maragos P, Paragios N (eds) European conference on computer vision, lecture notes in computer science, vol 6312. Springer, Berlin, pp 552–565

  51. Wu J (2012) Power mean svm for large scale visual classification. In: IEEE computer society conference on computer vision and pattern recognition, pp 2344–2351

  52. Wu J, Tan WC, Rehg JM (2011) Efficient and effective visual codebook generation using additive kernels. J Mach Learn Res 12:3097–3118

    MATH  MathSciNet  Google Scholar 

  53. Yu HF, Hsieh CJ, Chang KW, Lin CJ (2012) Large linear classification when data cannot fit in memory. ACM Trans Knowl Discov Data 5(4):23

    Article  Google Scholar 

  54. Yu K, Zhang T, Gong Y (2009) Nonlinear learning using local coordinate coding. In: Advances in neural information processing systems, pp 2223–2231

  55. Yuan GX, Ho CH, Lin CJ (2012) Recent advances of large-scale linear classification. Proc IEEE 100(9):2584–2603

    Article  Google Scholar 

  56. Zhou X, Yu K, Zhang T, Huang TS (2010) Image classification using super-vector coding of local image descriptors. In: European conference on computer vision, pp 141–154

Download references

Acknowledgments

This work was funded by Region Bretagne (France) and VIED (Vietnam International Education Development).

Author information

Authors and Affiliations

  1. An Giang University, An Giang, Vietnam

    Thanh-Nghi Doan

  2. Institut Telecom, Telecom Bretagne UMR CNRS 6285 Lab-STICC, Brest, France

    Thanh-Nghi Do

  3. Can Tho University, Can Tho, Vietnam

    Thanh-Nghi Do

  4. Université de Rennes 1, IRISA, Campus Universitaire de Beaulieu, 35042, Rennes Cedex, France

    François Poulet

Authors
  1. Thanh-Nghi Doan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thanh-Nghi Do
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. François Poulet
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Thanh-Nghi Doan.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Doan, TN., Do, TN. & Poulet, F. Large scale classifiers for visual classification tasks. Multimed Tools Appl 74, 1199–1224 (2015). https://doi.org/10.1007/s11042-014-2049-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-014-2049-4

Keywords

Search

Navigation