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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Data and code at https://github.com/haldai/LogicalVision2.
- 2.
Clock face angle between 12 and each hour position in \(\{1..12\}\).
- 3.
- 4.
Code also at https://github.com/haldai/LogicalVision2.
- 5.
The result can be reproduced and visualised by the example in Logical Vision 2 GitHub repository.
References
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)
Cecchini, R., Del Bimbo, A.: A programming environment for imaging applications. Pattern Recogn. Lett. 14(10), 817–824 (1993)
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1–27:27 (2011)
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
Cox, D.: Do we understand high-level vision? Curr. Opin. Neurobiol. 25, 187–193 (2014)
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
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)
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)
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)
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)
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)
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)
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)
Farid, R., Sammut, C.: Plane-based object categorisation using relational learning. Mach. Learn. 94(1), 3–23 (2014)
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)
Galilei, G.: The Herald of the Stars (1610). English translation by Edward Stafford Carlos, Rivingtons, London, 1880; edited by Peter Barker, Byzantium Press, 2004
Gregory, R.: Concepts and Mechanics of Perception. Duckworth, London (1974)
Gregory, R.: Eye and Brain: The Psychology of Seeing. Oxford University Press, Oxford (1998)
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)
von Helmholtz, H.: Treatise on Physiological Optics, vol. 3. Dover Publications, New York (1962). Originally published in German in 1825
Horn, B.: Obtaining Shape from Shading Information. MIT Press, Cambridge (1989)
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)
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)
Lake, B., Salakhutdinov, R., Tenenbaum, J.: Human-level concept learning through probabilistic program induction. Science 350, 1332–1338 (2015)
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)
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
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)
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)
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
Muggleton, S., Lin, D., Pahlavi, N., Tamaddoni-Nezhad, A.: Meta-interpretive learning: application to grammatical inference. Mach. Learn. 94, 25–49 (2014)
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)
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)
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)
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)
Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976–990 (2010)
Shanahan, M.: Perception as abduction: turning sensor data into meaningful representation. Cogn. Sci. 29(1), 103–134 (2005)
Vinyals, O., Blundell, C., Lillicrap, T.P., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. CoRR abs/1606.04080 (2016)
Wielemaker, J., Schrijvers, T., Triska, M., Lager, T.: SWI-prolog. Theor. Pract. Logic Program. 12(1–2), 67–96 (2012)
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)
Zhang, R., Tai, P., Cryer, J., Shah, M.: Shape-from-shading: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 21(8), 670–706 (1999)
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
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
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)