Skip to main content
SpringerLink
Log in

Addressing the Inevitable Imprecision: Multiple Instance Learning for Hyperspectral Image Analysis

  • Chapter
  • First Online:
Hyperspectral Image Analysis

Part of the book series: Advances in Computer Vision and Pattern Recognition ((ACVPR))

Abstract

In many remote sensing and hyperspectral image analysis applications, precise ground truth information is unavailable or impossible to obtain. Imprecision in ground truth often results from highly mixed or sub-pixel spectral responses over classes of interest, a mismatch between the precision of global positioning system (GPS) units and the spatial resolution of collected imagery, and misalignment between multiple sources of data. Given these sorts of imprecision, training of traditional supervised machine learning models which rely on the assumption of accurate and precise ground truth becomes intractable. Multiple instance learning (MIL) is a methodology that can be used to address these challenging problems. This chapter investigates the topic of hyperspectral image analysis given imprecisely labeled data and reviews MIL methods for hyperspectral target detection, classification, data fusion, and regression.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 169.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    The eFUMI implementation is available at: https://github.com/GatorSense/FUMI [40].

  2. 2.

    The MI-SMF and MI-ACE implementations are available at: https://github.com/GatorSense/MIACE [42].

  3. 3.

    The MI-HE implementation is available at: https://github.com/GatorSense/MIHE [54].

  4. 4.

    The MICI implementation is available at: https://github.com/GatorSense/MICI [60].

  5. 5.

    The MICIR implementation is available at: https://github.com/GatorSense/MICI [60].

  6. 6.

    The MIMRF implementation is available at: https://github.com/GatorSense/MIMRF [85].

References

  1. Gader P, Zare A, Close R et al (2013) MUUFL gulfport hyperspectral and lidar airborne data set. Technical report, University of Florida, Gainesville, FL, REP-2013-570. Data and code. https://github.com/GatorSense/MUUFLGulfport and Zenodo. https://doi.org/10.5281/zenodo.1186326

  2. Brigot G, Colin-Koeniguer E, Plyer A, Janez F (2016) Adaptation and evaluation of an optical flow method applied to coregistration of forest remote sensing images. IEEE J Sel Topics Appl Earth Observ 9(7):2923–2939

    Google Scholar 

  3. Cao S, Zhu X, Pan Y, and Yu Q (2014) A stable land cover patches method for automatic registration of multitemporal remote sensing images. IEEE J Sel Topics Appl Earth Observ 7(8):3502–3512

    Google Scholar 

  4. Dietterich TG, Lathrop RH, Lozano-Pérez T et al (1997) Solving the multiple instance problem with axis-parallel rectangles. Artif Intell 89(1–2):31–71

    Google Scholar 

  5. Maron O, Lozano-Perez T (1998) A framework for multiple-instance learning. In: Advances in neural information processing systems (NIPS), pp 570–576

    Google Scholar 

  6. Maron O, Ratan AL (1998) Multiple-instance learning for natural scene classification. In: International conference on machine learning, vol 98, pp 341–349

    Google Scholar 

  7. Zhang Q, Goldman SA (2002) EM-DD: an improved multiple-instance learning technique. In: Advances in neural information processing systems (NIPS), vol 2, pp 1073–1080

    Google Scholar 

  8. Press WH, Flannery BP, Teukolsky SA (1992) Numerical recipes in C: the art of scientific programming. Cambridge University Press, Cambridge

    Google Scholar 

  9. Andrews S, Tsochantaridis I, Hofmann T (2002) Support vector machines for multiple-instance learning. In: Advances in neural information processing systems (NIPS) 561–568

    Google Scholar 

  10. Shrivastava A, Pillai JK, Patel VM, Chellappa R (2014) Dictionary-based multiple instance learning. In: IEEE international conference on image processing (ICIP), pp 160–164

    Google Scholar 

  11. Shrivastava A, Patel VM, Pillai JK, Chellappa R (2015) Generalized dictionaries for multiple instance learning. Int J Comput Vis 114(2–3):288–305

    Google Scholar 

  12. Mallat SG, Zhang Z (1993) Matching pursuits with time-frequency dictionaries. IEEE Trans Signal Process 41(12):3397–3415

    Google Scholar 

  13. Aharon M, Elad M, Bruckstein A (2006) K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans Signal Process 54(11):4311–4322

    Google Scholar 

  14. Mairal J, Bach F, Ponce J (2012) Task-driven dictionary learning. IEEE Trans Pattern Anal Mach Intell 34(4):791–804

    Google Scholar 

  15. Wang X, Wang B, Bai X, Liu W, Tu Z (2013) Max-margin multiple-instance dictionary learning. In: International conference on machine learning, pp 846–854

    Google Scholar 

  16. Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation. J Mach Learn Res 3:993–1022

    MATH  Google Scholar 

  17. Fu Z et al (2011) MILIS: multiple instance learning with instance selection. IEEE Trans Pattern Anal Mach Intell 33(5):958–977

    Article  Google Scholar 

  18. Chen Y, Bi J, Wang JZ (2006) MILES: multiple-instance learning via embedded instance selection. IEEE Trans Pattern Anal Mach Intell 28(12):1931–1947

    Google Scholar 

  19. Zhu J, Rosset S, Hastie T, Tibshirani R (2004) 1-norm support vector machines. In: Advances in neural information processing systems (NIPS), vol 16, pp 49–56

    Google Scholar 

  20. Schölkopf B, Smola AJ (2002) Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT Press

    Google Scholar 

  21. Zhou Z, Xu J (2007) On the relation between multi-instance learning and semi-supervised learning. In: Proceedings of the 24th international conference on machine learning, pp 1167–1174

    Google Scholar 

  22. Hoffman J et al (2015) Detector discovery in the wild: joint multiple instance and representation learning. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 2883–2891

    Google Scholar 

  23. Li W, Vasconcelos N (2015) Multiple instance learning for soft bags via top instances. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 4277–4285

    Google Scholar 

  24. Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645

    Google Scholar 

  25. Zhang D, Meng D, Han J (2017) Co-saliency detection via a self-paced multiple-instance learning framework. IEEE Trans Pattern Anal Mach Intell 39(5):865–878

    Article  Google Scholar 

  26. Kumar MP, Packer B, Koller D (2010) Self-paced learning for latent variable models. In: Advances in neural information processing systems (NIPS), pp 1189–1197

    Google Scholar 

  27. Wang J (2000) Solving the multiple-instance problem: a lazy learning approach. In: Proceedings of the 17th international conference on machine learning, pp 1119–1125

    Google Scholar 

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

    MATH  Google Scholar 

  29. Huttenlocher DP et al (1993) Comparing images using the Hausdorff distance. IEEE Trans Pattern Anal Mach Intell 15(9):850–863

    Article  Google Scholar 

  30. Jiang L, Cai Z, Wang D et al (2014) Bayesian citation-KNN with distance weighting. Int J Mach Learn Cybern 5(2):193–199

    Article  Google Scholar 

  31. Ghosh D, Bandyopadhyay S (2015) A fuzzy citation-kNN algorithm for multiple instance learning. In: IEEE international conference on fuzzy systems, pp 1–8

    Google Scholar 

  32. Villar P, Montes R, Sánchez A et al (2016) Fuzzy-Citation-KNN: a fuzzy nearest neighbor approach for multi-instance classification. In: IEEE international conference on fuzzy systems, pp 946–952

    Google Scholar 

  33. Wang X, Yan Y, Tang P et al (2018) Revisiting multiple instance neural networks. Pattern Recognit 74:15–24

    Article  Google Scholar 

  34. Nasrabadi NM (2014) Hyperspectral target detection: an overview of current and future challenges. IEEE Signal Process Mag 31(1):34–44

    Google Scholar 

  35. Manolakis D, Marden D, Shaw GA (2003) Hyperspectral image processing for automatic target detection applications. Linc Lab J 14(1):79–116

    Google Scholar 

  36. Manolakis D, Truslow E, Pieper M, Cooley T, Brueggeman M (2014) Detection algorithms in hyperspectral imaging systems: an overview of practical algorithms. IEEE Signal Process Mag 31(1):24–33

    Google Scholar 

  37. Jiao C, Zare A (2015) Functions of multiple instances for learning target signatures. IEEE Trans Geosci Remote Sens 53(8):4670–4686

    Google Scholar 

  38. Zare A, Jiao C (2014) Extended functions of multiple instances for target characterization. In: IEEE workshop hyperspectral image signal process: evolution in remote sensing (WHISPERS), pp 1–4

    Google Scholar 

  39. Zare A, Gader P (2007) Sparsity promoting iterated constrained endmember detection for hyperspectral imagery. IEEE Geosci Remote Sens Lett 4(3):446–450

    Google Scholar 

  40. Jiao C, Zare A (2019) GatorSense/FUMI: initial release (Version v1.0). Zenodo. https://doi.org/10.5281/zenodo.2638304

  41. Zare Jiao C, Glenn T (2018) Discriminative multiple instance hyperspectral target characterization. IEEE Trans Pattern Anal Mach Intell 65(10):2634–2648

    Google Scholar 

  42. Zare A, Jiao C, Glenn T (2018). GatorSense/MIACE: version 1 (Version v1.0). Zenodo. https://doi.org/10.5281/zenodo.1467358

  43. Zare A, Ho KC (2014) Endmember variability in hyperspectral analysis: addressing spectral variability during spectral unmixing. IEEE Signal Process Mag 31(1):95–104

    Article  Google Scholar 

  44. Jiao C, Zare A (2017) Multiple instance hybrid estimator for learning target signatures. In: IEEE international geoscience and remote sensing symposium, pp 1–4

    Google Scholar 

  45. Jiao C et al (2018) Multiple instance hybrid estimator for hyperspectral target characterization and sub-pixel target detection. ISPRS J Photogramm Remote Sens 146:232–250

    Article  Google Scholar 

  46. Broadwater J, Chellappa R (2007) Hybrid detectors for subpixel targets. IEEE Trans Pattern Anal Mach Intell 29(11):1891–1903

    Google Scholar 

  47. Babenko B, Dollár P, Tu Z, Belongie S (2008) Simultaneous learning and alignment: multi-instance and multi-pose learning. In: Workshop on faces in ‘Real-Life’ images: detection, alignment, and recognition

    Google Scholar 

  48. Ramirez I, Sprechmann P, Sapiro G (2010) Classification and clustering via dictionary learning with structured incoherence and shared features. In: IEEE conference on computer vision and pattern recognition, pp 3501–3508

    Google Scholar 

  49. Yang M, Zhang L, Feng X, Zhang D (2014) Sparse representation based fisher discrimination dictionary learning for image classification. Int J Comput Vis 109(3):209–232

    Article  MathSciNet  MATH  Google Scholar 

  50. Yang M, Zhang L, Feng X, Zhang D (2011) Fisher discrimination dictionary learning for sparse representation. In: International conference on computer vision, pp 543–550

    Google Scholar 

  51. Figueiredo MAT, Nowak RD (2003) An EM algorithm for wavelet-based image restoration. IEEE Trans Image Process 12(8):906–916

    Google Scholar 

  52. Daubechies I, Defrise M, De Mol C (2003) An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun Pure Appl Math 57(11):1413–1457

    Google Scholar 

  53. Nascimento JMP, Dias JMB (2005) Vertex component analysis: a fast algorithm to unmix hyperspectral data. IEEE Trans Geosci Remote Sens 43(4):898–910

    Google Scholar 

  54. Jiao C, Zare A (2018) GatorSense/MIHE: initial release (Version 0.1). Zenodo. https://doi.org/10.5281/zenodo.1320109

  55. Zhong P, Gong Z, Shan J (2019) Multiple instance learning for multiple diverse hyperspectral target characterizations. IEEE Trans Neural Netw Learn Syst 31(1): 246–258

    Google Scholar 

  56. Baldridge AM, Hook SJ, Grove CI, Rivera G (2009) The ASTER spectral library version 2.0. Remote Sens Environ 113(4):711–715

    Google Scholar 

  57. Kraut S, Scharf LL (1999) The CFAR adaptive subspace detector is a scale-invariant GLRT. IEEE Trans Signal Process 47(9):2538–2541

    Google Scholar 

  58. Chang C, Lin C (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1–27

    Google Scholar 

  59. Glenn T, Zare A, Gader P, Dranishnikov D (2013) Bullwinkle: scoring code for sub-pixel targets (Version 1.0) [Software]. https://github.com/GatorSense/MUUFLGulfport/

  60. Du X, Zare A (2019) GatorSense/MICI: initial release (Version v1.0). Zenodo. https://doi.org/10.5281/zenodo.2638378

  61. Du X, Zare A, Keller JM, Anderson DT (2016) Multiple Instance Choquet integral for classifier fusion. IEEE Congr Evol Comput 1054–1061

    Google Scholar 

  62. Du X, Zare A (2019) Multiple instance Choquet integral classifier fusion and regression for remote sensing applications. IEEE Trans Geosci Remote Sens 57(5):2741–2753

    Article  Google Scholar 

  63. Choquet G (1954) Theory of capacities. Ann L’Institut Fourier 5:131–295

    Article  MathSciNet  MATH  Google Scholar 

  64. Keller JM, Liu D, Fogel DB (2016) Fundamentals of computational intelligence: neural networks, fuzzy systems and evolutionary computation. IEEE press series on computational intelligence, Wiley

    Google Scholar 

  65. Rolewicz S (2013) Functional analysis and control theory: linear systems. Springer Science & Business Media, Dordrecht, The Netherlands

    Google Scholar 

  66. Du X (2017) Multiple instance choquet integral for multiresolution sensor fusion. Doctoral dissertation, University of Missouri, Columbia, MO, USA

    Google Scholar 

  67. Wang Z, Radosavljevic V, Han B et al (2008) Aerosol optical depth prediction from satellite observations by multiple instance regression. In: Proceedings of the SIAM international conference on data mining, pp 165–176

    Google Scholar 

  68. Wang Z, Lan L, Vucetic S (2012) Mixture model for multiple instance regression and applications in remote sensing. IEEE Trans Geosci Remote Sens 50(6):2226–2237

    Article  Google Scholar 

  69. Wagstaff KL, Lane T (2007) Salience assignment for multiple-instance regression. In: International conference on machine learn, workshop on constrained optimization and structured output spaces

    Google Scholar 

  70. Wagstaff KL, Lane T, Roper A (2008) Multiple-instance regression with structured data. In: IEEE international conference on data mining workshops, pp 291–300

    Google Scholar 

  71. Ray S, Page D (2001) Multiple instance regression. In: Proceedings of the 18th international conference on machine learning, vol 1, pp 425–432

    Google Scholar 

  72. Dooly DR, Zhang Q, Goldman SA, Amar RA (2002) Multiple-instance learning of real-valued data. J Mach Learn Res 3:651–678

    MATH  Google Scholar 

  73. Goldman SA, Scott SD (2003) Multiple-instance learning of real-valued geometric patterns. Ann Math Artif Intell 39(3):259–290

    Article  MathSciNet  MATH  Google Scholar 

  74. Haussler D (1992) Decision theoretic generalizations of the PAC model for neural net and other learning applications. Inf Comput 100(1):78–150

    Google Scholar 

  75. Kearns MJ, Schapire RE, Sellie LM (1994) Toward efficient agnostic learning. Mach Learn 17(2–3):115–141

    MATH  Google Scholar 

  76. Kivinen J, Warmuth MK (1997) Exponentiated gradient versus gradient descent for linear predictors. Inf Comput 132(1):1–63

    Google Scholar 

  77. Wang ZG, Zhao ZS, Zhang CS (2013) Online multiple instance regression. Chin Phys B 22(9):098702

    Article  Google Scholar 

  78. Dooly DR, Goldman SA, Kwek SS (2006) Real-valued multiple-instance learning with queries. J Comput Syst Sci 72(1):1–5

    Article  MathSciNet  MATH  Google Scholar 

  79. Cheung PM, Kwok JT (2006) A regularization framework for multiple-instance learning. In: Proceedings of the 23rd international conference on machine learning, pp 193–200

    Google Scholar 

  80. Gärtner T, Flach PA, Kowalczyk A, Smola AJ. Multi-instance kernels. In: Proceedings of the 19th international conference on machine learning, vol 2, no 3, pp 179–186

    Google Scholar 

  81. Gunn SR (1998) Support vector machines for classification and regression. ISIS Tech Rep 14(1):5–16

    Google Scholar 

  82. Trabelsi M, Frigui H (2019) Robust fuzzy clustering for multiple instance regression. Pattern Recognit

    Google Scholar 

  83. Krishnapuram R, Keller JM (1993) A possibilistic approach to clustering. IEEE Trans Fuzzy Syst 1(2):98–110

    Article  Google Scholar 

  84. Davis J, Santos Costa V, Ray S, Page D (2007) Tightly integrating relational learning and multiple-instance regression for real-valued drug activity prediction. In: Proceedings on international conference on machine learning, vol 287

    Google Scholar 

  85. Du X, Zare A (2019) GatorSense/MIMRF: initial release (Version v1.0). Zenodo. https://doi.org/10.5281/zenodo.2638382

  86. Du X, Zare A (2019) Multiresolution multimodal sensor fusion for remote sensing data with label uncertainty. IEEE Trans Geosci Remote Sens, In Press

    Google Scholar 

  87. Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S (2010) Slic superpixels. Ecole Polytechnique Fédéral de Lausssanne (EPFL). Tech Rep 149300:155–162

    Google Scholar 

  88. Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S (2012) SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282

    Article  Google Scholar 

  89. OSM contributors (2018) Open street map. https://www.openstreetmap.org

  90. Google (2018) Google earth. https://www.google.com/earth/

  91. Google (2018) Google maps. https://www.google.com/maps/

  92. Du X, Zare A (2017) Technical report: scene label ground truth map for MUUFL gulfport data set. University of Florida, Gainesville, FL, Tech Rep 20170417. http://ufdc.ufl.edu/IR00009711/00001

Download references

Author information

Authors and Affiliations

  1. Xidian University, Xi’an, China

    Changzhe Jiao

  2. University of Michigan, Ann Arbor, USA

    Xiaoxiao Du

  3. University of Florida, Gainesville, USA

    Alina Zare

Authors
  1. Changzhe Jiao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaoxiao Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Alina Zare
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alina Zare .

Editor information

Editors and Affiliations

  1. Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA

    Saurabh Prasad

  2. CNRS, Grenoble INP, GIPSA-lab, Université Grenoble Alpes, Grenoble, France

    Jocelyn Chanussot

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Jiao, C., Du, X., Zare, A. (2020). Addressing the Inevitable Imprecision: Multiple Instance Learning for Hyperspectral Image Analysis. In: Prasad, S., Chanussot, J. (eds) Hyperspectral Image Analysis. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-030-38617-7_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-38617-7_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-38616-0

  • Online ISBN: 978-3-030-38617-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation