Advertisement

SceneNet: A Perceptual Ontology for Scene Understanding

  • Ilan KadarEmail author
  • Ohad Ben-Shahar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8926)

Abstract

Scene recognition systems which attempt to deal with a large number of scene categories currently lack proper knowledge about the perceptual ontology of scene categories and would enjoy significant advantage from a perceptually meaningful scene representation. In this work we perform a large-scale human study to create “SceneNet”, an online ontology database for scene understanding that organizes scene categories according to their perceptual relationships. This perceptual ontology suggests that perceptual relationships do not always conform the semantic structure between categories, and it entails a lower dimensional perceptual space with “perceptually meaningful” Euclidean distance, where each embedded category is represented by a single prototype. Using the SceneNet ontology and database we derive a computational scheme for learning non-linear mapping of scene images into the perceptual space, where each scene image is closest to its category prototype than to any other prototype by a large margin. Then, we demonstrate how this approach facilitates improvements in large-scale scene categorization over state-of-the-art methods and existing semantic ontologies, and how it reveals novel perceptual findings about the discriminative power of visual attributes and the typicality of scenes.

Keywords

Scene understanding Scene gist recognition Scene categories Perceptual relations Perceptual space 

References

  1. 1.
    Xiao, J., Hays, J., Ehinger, K., Oliva, A., Torralba, A.: Sun database: Large scale scene recognition from abbey to zoo. In: CVPR (2010)Google Scholar
  2. 2.
    SceneNet: An Online Perceptual Ontology Database for Scene Understanding. (2013) Anonymous URL. Concealed for blind reviewGoogle Scholar
  3. 3.
    Fei-Fei, L., Perona, P.: A bayesian hierarchy model for learning natural scene categories. In: CVPR (2005)Google Scholar
  4. 4.
    Bosch, A., Zisserman, A., Muñoz, X.: Scene Classification Via pLSA. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 517–530. Springer, Heidelberg (2006) CrossRefGoogle Scholar
  5. 5.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR, pp. 2169–2178 (2006)Google Scholar
  6. 6.
    Griffin, G., Perona, P.: Learning and using taxonomies for fast visual categorization. In: CVPR (2008)Google Scholar
  7. 7.
    Bart, E., Porteous, I., Perona, P., Welling, M.: Unsupervised learning of visual taxonomies. In: CVPR (2008)Google Scholar
  8. 8.
    Ahuja, N., Todorovic, S.: Learning the taxonomy and models of categories present in arbitrary images. In: ICCV (2007)Google Scholar
  9. 9.
    Marszałek, M., Schmid, C.: Constructing Category Hierarchies for Visual Recognition. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 479–491. Springer, Heidelberg (2008) CrossRefGoogle Scholar
  10. 10.
    Sivic, J., Russell, B., Zisserman, A., Freeman, W., Efros, A.: Unsupervised discovery of visual object class hierarchies. In: CVPR (2008)Google Scholar
  11. 11.
    Li, L., Wang, C., Lim, Y., Blei, D., Fei-Fei, L.: Building and using a semantivisual image hierarchy. In: CVPR (2010)Google Scholar
  12. 12.
    Marszalek, M., Schmid, C.: Semantic hierarchies for visual object recognition. In: CVPR (2007)Google Scholar
  13. 13.
    Torralba, A., Fergus, R., W.T., F.: 80 million tiny images: a large dataset for non-parametric object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 30(11), 1958–1970 (2008)CrossRefGoogle Scholar
  14. 14.
    Fergus, R., Bernal, H., Weiss, Y., Torralba, A.: Semantic Label Sharing for Learning with Many Categories. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 762–775. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  15. 15.
    Deselaers, T., Ferrari, V.: Visual and semantic similarity in imagenet. In: CVPR, pp. 1777–1784 (2011)Google Scholar
  16. 16.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: CVPR (2009)Google Scholar
  17. 17.
    Verma, N., Mahajan, D., Sellamanickam, S., Nair, V.: Learning hierarchical similarity metrics. In: CVPR (2012)Google Scholar
  18. 18.
    Miller, G.: Wordnet: A lexical database for english. In: Communications of the ACM (1995)Google Scholar
  19. 19.
    Deng, J., Berg, A., Fei-Fei, L.: Hierarchical semantic indexing for large scale image retrieval. In: CVPR (2011)Google Scholar
  20. 20.
    Weinberger, K., Chapelle, O.: Large margin taxonomy embedding for document categorization. In: NIPS, pp. 1737–1744 (2008)Google Scholar
  21. 21.
    Kadar, I., Ben-Shahar, O.: Small sample scene categorization from perceptual relations. In: CVPR, pp. 2711–2718 (2012)Google Scholar
  22. 22.
    Rousselet, G.A., Fabre-Thorpe, M., Thorpe, S.J.: Parallel processing in high-level categorization of natural images. Nature Neuroscience 5(7), 629–630 (2002)Google Scholar
  23. 23.
    Torgerson, W.S.: Multidimensional scaling: theory and method. Psychometrika 17(6), 401–419 (1952)CrossRefzbMATHMathSciNetGoogle Scholar
  24. 24.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. Int. J. Comput. Vision 42(3), 145–175 (2001)CrossRefzbMATHGoogle Scholar
  25. 25.
    Greene, M., Oliva, A.: Forest before the trees: the precedence of global features in visual perception. Cognit. Sci. 58, 137–179 (2009)Google Scholar
  26. 26.
    Patterson, G., Hays, J.: SUN attribute database: Discovering, annotating, and recognizing scene attributes. In: CVPR (2012)Google Scholar
  27. 27.
    Saunders, C., Gammerman, A., Vovk, V.: Ridge regression learning algorithm in dual variables. In: ICML, p. 515521 (1998)Google Scholar
  28. 28.
    Boyd, S., Vandenberghe, L. (eds.): Convex Optimization. Cambridge University Press (2004)Google Scholar
  29. 29.
    Weinberger, K., Saul, L.: Fast solvers and efficient implementations for distance metric learning. In: ICML, pp. 1160–1167 (2008)Google Scholar
  30. 30.
    Vogel, J., Schiele, B.: Semantic typicality measure for natural scene categorization. In: Annual Pattern Recognition Symposium (2004)Google Scholar
  31. 31.
    Ehinger, K., Xiao, J., Torralba, A., Oliva, A.: Estimating scene typicality from human ratings and image features. In: Proceedings of the 33rd Annual Conference of the Cognitive Science Society, pp. 2562–2567 (2011)Google Scholar
  32. 32.
    Murphy, G.L. (ed.): The big book of concepts. MIT Press (2002)Google Scholar
  33. 33.
    Rosch, E.: Cognitive representations of semantic categories. J. Exp. Psych. (1975)Google Scholar
  34. 34.
    Mervis, C., Pani, J.: Acquisition of basic object categories. Cognit. Sci. 12 (1980)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Ben-Gurion University of the NegevBeer-ShevaIsrael

Personalised recommendations