Abstract
Fisher vector encoding from deep architectures has shown significant improvement in the performance of classification and retrieval tasks. Despite significant benefit of Fisher vectors for classification and retrieval problems, they suffer from the problem of high dimensionality giving rise to computational and storage overhead for large scale learning problems. This chapter provides guidelines for tackling this issue by either deploying feature selection or compression methods. We provide an overview of all the popular feature selection and compression techniques and identify some metrics that can help practitioners identify the appropriateness of each technique used for the cause.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lowe, D.: Object recognition from local scale-invariant features. International Conference on Computer Vision (ICCV) 2, 1150–1157 (1999)
Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1794–1801. IEEE (2009)
Csurka, G., Dance, C., Bray, C., et al.: Visual categorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision (ECCV), pp. 1–22 (2004)
Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos. In: null, p. 1470. IEEE (2003)
Perronnin, F., Sanchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: European Conference on Computer Vision, pp. 143–156. Springer (2010)
Akata, Z., Perronnin, F., Harchaoui, Z., et al.: Good practice in large-scale learning for image classification. IEEE Trans. Pattern Anal. Mach. Intell. 3, 507–520 (2014)
Simonyan, K., Parkhi, O., Vedaldi, A., Zisserman, A.: Fisher vector faces in the wild. In: BMVC, vol. 2, p. 4 (2013)
Holub, A., Welling, M., Perona, P.: Combining generative models and fisher kernels for object class recognition. In: ICCV, pp. 136–143 (2005)
Perronnin, F., Dance, C.: Fisher kernels on visual vocabularies for image categorization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2007)
Sanchez, J., Perronnin, F.: High-dimensional signature compression for large-scale image classification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2011, 1665–1672 (2011)
Csurka, G., Perronnin, F.: Fisher vectors: beyond bag-of-visual-words image representations. In: Richard, P., Braz, J. (eds.) Computer Vision, Imaging and Computer Graphics Theory and Applications. Communications in Computer and Information Science, vol. 229, pp. 28–42. Springer, Berlin (2011)
Sanchez, J., Perronnin, F., Mensink, T., Verbeek, J.: Image classification with the fisher vector: theory and practice. Technical Report RR-8209, INRIA (2013)
Chatfield, K., Lempitsky, V., Vedaldi, A., Zisserman, A.: The devil is in the details: an evaluation of recent feature encoding methods. In: Proceedings of BMVC, pp. 76.1–76.12. https://doi.org/10.5244/C.25.76 (2011)
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Azim, T.: Fisher kernels match deep models. Electron. Lett. 53(6), 397–399 (2017)
Perronnin, F., Larlus, D.: Fisher vectors meet neural networks: a hybrid classification architecture. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3743–3752 (2015)
Huang, P.S., Avron, H., Sainath, T., et al.: Kernel methods match deep neural networks on TIMIT. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 205–209. IEEE (2014)
Zeiler, M., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision, pp. 818–833. Springer (2014)
Yu Zhang, J.W., Cai, J.: Compact representation for image classification: to choose or to compress? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 907–914 (2014)
Chen, S., Liu, H., Zeng, X., et al.: Local patch vectors encoded by fisher vectors for image classification. Information 9(2), 38 (2018)
Fred, A., De Marsico, M.: Pattern recognition applications and methods, pp. 80–98
Oliveira, F., Levkowitz, H.: From visual data exploration to visual data mining: a survey. IEEE Trans. Visual Comput. Graphics 9(3), 378–394 (2003)
Ham, J., Lee, D., Mika, S., et al.: A kernel view of the dimensionality reduction of manifolds. In: Proceedings of the Twenty-first International Conference on Machine Learning, p. 47. ACM (2004)
Maaten, L., Postma, E.: Dimensionality reduction: a comparative. J. Mach. Learn. Res., 66–71 (2009)
Vlachos, M., Domeniconi, C., Gunopulos, D., et al.: Non-linear dimensionality reduction techniques for classification and visualization. In: Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 645–651. ACM (2002)
Jolliffe, I.: Principal component analysis: Wiley online library. Google Scholar (2002)
Torgerson, W.: Multidimensional scaling: I: theory and method. Psychometrika, 401–419 (1952)
Ben-Bassat, M.: Pattern recognition and reduction of dimensionality. Handb. Stat. 1982, 773–910 (1982)
Kira, K., Rendell, L.: A practical approach to feature selection. In: Machine Learning Proceedings 1992, pp. 249–256. Elsevier (1992)
Robnik, M., Kononenko, G.: Theoretical and empirical analysis of relieff and rrelieff. Mach. Learn., 23–69 (2003)
Koller, D., Sahami, M.: Toward Optimal Feature Selection. Technical report, Stanford InfoLab (1996)
Peng, H., Long, F., Ding, C.: Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27(8), 1226–1238 (2005)
Hall, M., Smith, L.: Feature selection for machine learning: comparing a correlation-based filter approach to the wrapper. FLAIRS Conference 1999, 235–239 (1999)
Kohavi, R., John, G.: Wrappers for feature subset selection. Artif. Intell., 273–324 (1997)
Ahmed, S., Azim, T.: Compression techniques for deep fisher vectors. In: ICPRAM, pp. 217–224 (2017)
Ahmed, S., Azim, T.: Condensing Deep Fisher Vectors: To Choose or to Compress? In: ICPRAM. Extended Papers, Series: LNCS, Subseries: Image Processing, Computer Vision, Pattern Recognition, and Graphics, pp. 80–98. Springer, Cham (2017)
Gulgezen, G., Cataltepe, Z., Yu, L.: Stable and accurate feature selection. In: Machine Learning and Knowledge Discovery in Databases, pp. 455–468. Springer, Berlin (2009)
Maaten, L.: Learning a parametric embedding by preserving local structure. In: Artificial Intelligence and Statistics, pp. 384–391 (2009)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2018 The Author(s), under exclusive licence to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Azim, T., Ahmed, S. (2018). Large Scale Image Retrieval and Its Challenges. In: Composing Fisher Kernels from Deep Neural Models. SpringerBriefs in Computer Science. Springer, Cham. https://doi.org/10.1007/978-3-319-98524-4_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-98524-4_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-98523-7
Online ISBN: 978-3-319-98524-4
eBook Packages: Computer ScienceComputer Science (R0)