Skip to main content
SpringerLink
Log in

Logical Vision: One-Shot Meta-Interpretive Learning from Real Images

  • Conference paper
  • First Online:
Inductive Logic Programming (ILP 2017)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10759))

Included in the following conference series:

Abstract

Statistical machine learning is widely used in image classification. However, most techniques (1) require many images to achieve high accuracy and (2) do not provide support for reasoning below the level of classification, and so are unable to support secondary reasoning, such as the existence and position of light sources and other objects outside the image. In recent work an Inductive Logic Programming approach called Logical Vision (LV) was shown to overcome some of these limitations. LV uses Meta-Interpretive Learning combined with low-level extraction of high-contrast points sampled from the image to learn recursive logic programs describing the image. This paper extends LV by using (a) richer background knowledge enabling secondary reasoning from raw images, such as light reflection that can itself be learned and used for resolving visual ambiguities, which cannot be easily modelled using statistical approaches, (b) a wider class of background models representing classical 2D shapes such as circles and ellipses, (c) primitive-level statistical estimators to handle noise in real images. Our results indicate that the new noise-robust version of LV is able to handle secondary reasoning task in real images with few data, which is very similar to scientific discovery process of humans. Specifically, it uses a single example (i.e. one-shot LV) converges to an accuracy at least comparable to thirty-shot statistical machine learner on the prediction of hidden light sources. Moreover, we demonstrate that the learned theory can be used to identify ambiguities in the convexity/concavity of objects such as craters.

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight 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.

    Data and code at https://github.com/haldai/LogicalVision2.

  2. 2.

    Clock face angle between 12 and each hour position in \(\{1..12\}\).

  3. 3.

    http://www.universetoday.com/118616/do-you-see-a-mountain-or-a-crater-in-this-picture/.

  4. 4.

    Code also at https://github.com/haldai/LogicalVision2.

  5. 5.

    The result can be reproduced and visualised by the example in Logical Vision 2 GitHub repository.

References

  1. Antanas, L., van Otterlo, M., Oramas Mogrovejo, J., Tuytelaars, T., De Raedt, L.: There are plenty of places like home: using relational representations in hierarchies for distance-based image understanding. Neurocomputing 123, 75–85 (2014)

    Article  Google Scholar 

  2. Cecchini, R., Del Bimbo, A.: A programming environment for imaging applications. Pattern Recogn. Lett. 14(10), 817–824 (1993)

    Article  MATH  Google Scholar 

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

    Article  Google Scholar 

  4. Cohn, A.G., Hogg, D.C., Bennett, B., Devin, V., Galata, A., Magee, D.R., Needham, C., Santos, P.: Cognitive vision: integrating symbolic qualitative representations with computer vision. In: Christensen, H.I., Nagel, H.-H. (eds.) Cognitive Vision Systems. LNCS, vol. 3948, pp. 221–246. Springer, Heidelberg (2006). https://doi.org/10.1007/11414353_14

    Chapter  Google Scholar 

  5. Cox, D.: Do we understand high-level vision? Curr. Opin. Neurobiol. 25, 187–193 (2014)

    Article  Google Scholar 

  6. Cropper, A., Muggleton, S.H.: Logical minimisation of meta-rules within meta-interpretive learning. In: Davis, J., Ramon, J. (eds.) ILP 2014. LNCS (LNAI), vol. 9046, pp. 62–75. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-23708-4_5

    Chapter  Google Scholar 

  7. Cropper, A., Muggleton, S.: Learning higher-order logic programs through abstraction and invention. In: Proceedings of the 25th International Joint Conference Artificial Intelligence, pp. 1418–1424 (2016)

    Google Scholar 

  8. Cucchiara, R., Piccardi, M., Mello, P.: Image analysis and rule-based reasoning for a traffic monitoring system. IEEE Trans. Intell. Transp. Syst. 1(2), 119–130 (2000)

    Article  Google Scholar 

  9. Dai, W.-Z., Muggleton, S.H., Zhou, Z.-H.: Logical vision: meta-interpretive learning for simple geometrical concepts. In: Late Breaking Paper Proceedings of the 25th International Conference on Inductive Logic Programming, pp. 1–16. CEUR (2015)

    Google Scholar 

  10. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the 13rd IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, pp. 886–893. IEEE Computer Society (2005)

    Google Scholar 

  11. Del Bimbo, A., Vicario, E., Zingoni, D.: A spatial logic for symbolic description of image contents. J. Vis. Lang. Comput. 5(3), 267–286 (1994)

    Article  Google Scholar 

  12. Duan, K., Parikh, D., Crandall, D.J., Grauman, K.: Discovering localized attributes for fine-grained recognition. In: Proceedings of the 25th IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, pp. 3474–3481. IEEE Computer Society (2012)

    Google Scholar 

  13. Esposito, F., Ferilli, S., Basile, T.M.A., Di Mauro, N.: Machine learning for digital document processing: from layout analysis to metadata extraction. Mach. Learn. Doc. Anal. Recogn. 90, 105–138 (2008)

    Google Scholar 

  14. Farid, R., Sammut, C.: Plane-based object categorisation using relational learning. Mach. Learn. 94(1), 3–23 (2014)

    Article  MathSciNet  Google Scholar 

  15. Ferilli, S., Basile, T.M., Esposito, F., Biba, M.: A contour-based progressive technique for shape recognition. In: Proceedings of 2011 International Conference on Document Analysis and Recognition, pp. 723–727 (2011)

    Google Scholar 

  16. Galilei, G.: The Herald of the Stars (1610). English translation by Edward Stafford Carlos, Rivingtons, London, 1880; edited by Peter Barker, Byzantium Press, 2004

    Google Scholar 

  17. Gregory, R.: Concepts and Mechanics of Perception. Duckworth, London (1974)

    Google Scholar 

  18. Gregory, R.: Eye and Brain: The Psychology of Seeing. Oxford University Press, Oxford (1998)

    Google Scholar 

  19. Heath, D., Ventura, D.: Before a computer can draw, it must first learn to see. In: Proceedings of the 7th International Conference on Computational Creativity, pp. 172–179 (2016)

    Google Scholar 

  20. von Helmholtz, H.: Treatise on Physiological Optics, vol. 3. Dover Publications, New York (1962). Originally published in German in 1825

    Google Scholar 

  21. Horn, B.: Obtaining Shape from Shading Information. MIT Press, Cambridge (1989)

    Google Scholar 

  22. Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., Darrell, T.: Natural language object retrieval. In: Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, pp. 4555–4564. IEEE Computer Society (2016)

    Google Scholar 

  23. Lake, B., Salakhutdinov, R., Gross, J., Tenenbaum, J.: One shot learning of simple visual concepts. In: Proceedings of the 33rd Annual Conference of the Cognitive Science Society, pp. 2568–2573 (2011)

    Google Scholar 

  24. Lake, B., Salakhutdinov, R., Tenenbaum, J.: Human-level concept learning through probabilistic program induction. Science 350, 1332–1338 (2015)

    Article  MathSciNet  MATH  Google Scholar 

  25. Lampert, C.H., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot visual object categorization. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 453–465 (2014)

    Article  Google Scholar 

  26. Li, Z., Gavves, E., Mensink, T., Snoek, C.G.M.: Attributes make sense on segmented objects. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VI. LNCS, vol. 8694, pp. 350–365. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10599-4_23

    Chapter  Google Scholar 

  27. Lin, D., Dechter, E., Ellis, K., Tenenbaum, J., Muggleton, S.: Bias reformulation for one-shot function induction. In: Proceedings of the 23rd European Conference on Artificial Intelligence (ECAI 2014), pp. 525–530. IOS Press, Amsterdam (2014)

    Google Scholar 

  28. Mensink, T., Verbeek, J.J., Csurka, G.: Learning structured prediction models for interactive image labeling. In: The 24th IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, pp. 833–840. IEEE Computer Society (2011)

    Google Scholar 

  29. Muggleton, S.H., Lin, D., Chen, J., Tamaddoni-Nezhad, A.: MetaBayes: Bayesian meta-interpretative learning using higher-order stochastic refinement. In: Zaverucha, G., Santos Costa, V., Paes, A. (eds.) ILP 2013. LNCS (LNAI), vol. 8812, pp. 1–17. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-44923-3_1

    Chapter  Google Scholar 

  30. Muggleton, S., Lin, D., Pahlavi, N., Tamaddoni-Nezhad, A.: Meta-interpretive learning: application to grammatical inference. Mach. Learn. 94, 25–49 (2014)

    Article  MathSciNet  MATH  Google Scholar 

  31. Muggleton, S., Lin, D., Tamaddoni-Nezhad, A.: Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited. Mach. Learn. 100(1), 49–73 (2015)

    Article  MathSciNet  MATH  Google Scholar 

  32. Muggleton, S., Raedt, L.D., Poole, D., Bratko, I., Flach, P., Inoue, K.: ILP turns 20: biography and future challenges. Mach. Learn. 86(1), 3–23 (2011)

    Article  MathSciNet  MATH  Google Scholar 

  33. Ojala, T., Pietikainen, M., Mäenpää, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971–987 (2002)

    Article  MATH  Google Scholar 

  34. Palatucci, M., Pomerleau, D., Hinton, G., Mitchell, T.M.: Zero-shot learning with semantic output codes. In: Advances in Neural Information Processing Systems, vol. 22, pp. 1410–1418. Curran Associates Inc. (2009)

    Google Scholar 

  35. Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976–990 (2010)

    Article  Google Scholar 

  36. Shanahan, M.: Perception as abduction: turning sensor data into meaningful representation. Cogn. Sci. 29(1), 103–134 (2005)

    Article  Google Scholar 

  37. Vinyals, O., Blundell, C., Lillicrap, T.P., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. CoRR abs/1606.04080 (2016)

    Google Scholar 

  38. Wielemaker, J., Schrijvers, T., Triska, M., Lager, T.: SWI-prolog. Theor. Pract. Logic Program. 12(1–2), 67–96 (2012)

    Article  MathSciNet  MATH  Google Scholar 

  39. Zhang, H., Fritts, J.E., Goldman, S.A.: Image segmentation evaluation: a survey of unsupervised methods. Comput. Vis. Image Underst. 110(2), 260–280 (2008)

    Article  Google Scholar 

  40. Zhang, R., Tai, P., Cryer, J., Shah, M.: Shape-from-shading: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 21(8), 670–706 (1999)

    MATH  Google Scholar 

Download references

Acknowledgements

This research was supported by the National Science Foundation of China (61751306). The second author acknowledges support from his Royal Academy of Engineering/Syngenta Research Chair at the Department of Computing at Imperial College London. Authors want to thank reviewers and ILP’17 attendees for helpful comments.

Author information

Authors and Affiliations

  1. National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China

    Wang-Zhou Dai & Zhi-Hua Zhou

  2. Department of Computing, Imperial College London, London, UK

    Stephen Muggleton

  3. School of Computer and Information Technology, Shanxi University, Taiyuan, China

    Jing Wen

  4. Department of Computer Science, University of Surrey, Guildford, UK

    Alireza Tamaddoni-Nezhad

Authors
  1. Wang-Zhou Dai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Stephen Muggleton
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jing Wen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Alireza Tamaddoni-Nezhad
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhi-Hua Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wang-Zhou Dai .

Editor information

Editors and Affiliations

  1. University of Strasbourg, Strasbourg, France

    Nicolas Lachiche

  2. University of Orléans, Orléans, France

    Christel Vrain

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer International Publishing AG, part of Springer Nature

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Dai, WZ., Muggleton, S., Wen, J., Tamaddoni-Nezhad, A., Zhou, ZH. (2018). Logical Vision: One-Shot Meta-Interpretive Learning from Real Images. In: Lachiche, N., Vrain, C. (eds) Inductive Logic Programming. ILP 2017. Lecture Notes in Computer Science(), vol 10759. Springer, Cham. https://doi.org/10.1007/978-3-319-78090-0_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-78090-0_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-78089-4

  • Online ISBN: 978-3-319-78090-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation