Advertisement

Discovering a Lexicon of Parts and Attributes

  • Subhransu Maji
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7585)

Abstract

We propose a framework to discover a lexicon of visual attributes that supports fine-grained visual discrimination. It consists of a novel annotation task where annotators are asked to describe differences between pairs of images. This captures the intuition that for a lexicon to be useful, it should achieve twin goals of discrimination and communication. Next, we show that such comparative text collected for many pairs of images can be analyzed to discover topics that encode nouns and modifiers, as well as relations that encode attributes of parts. The model also provides an ordering of attributes based on their discriminative ability, which can be used to create a shortlist of attributes to collect for a dataset. Experiments on Caltech-UCSD birds, PASCAL VOC person, and a dataset of airplanes, show that the discovered lexicon of parts and their attributes is comparable to those created by experts.

Keywords

Latent Dirichlet Allocation Object Category Visual Attribute Front Wheel Sentence Pair 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Kumar, N., Belhumeur, P., Nayar, S.: FaceTracer: A Search Engine for Large Collections of Images with Faces. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 340–353. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  2. 2.
    Farhadi, A., Endres, I., Hoiem, D.: Attribute-centric recognition for cross-category generalization. In: CVPR (2010)Google Scholar
  3. 3.
    Bourdev, L., Maji, S., Malik, J.: Describing people: A poselet-based approach to attribute classification. In: ICCV (2011)Google Scholar
  4. 4.
    MTurk: Amazon mechanical turk, http://www.mturk.com
  5. 5.
    Berg, T.L., Berg, A.C., Shih, J.: Automatic Attribute Discovery and Characterization from Noisy Web Data. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 663–676. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  6. 6.
    Parikh, D., Grauman, K.: Interactive discovery of task-specific nameable attributes. In: Workshop on Fine-Grained Visual Categorization, CVPR (2011)Google Scholar
  7. 7.
    Duan, K., Bloomington, I., Parikh, D., Grauman, K.: Discovering localized attributes for fine-grained recognition. In: CVPR (2012)Google Scholar
  8. 8.
    Brown, P.F., Cocke, J., Pietra, S.A.D., Pietra, V.J.D., Jelinek, F., Lafferty, J.D., Mercer, R.L., Roossin, P.S.: A statistical approach to machine translation. Comput. Linguist. (1990)Google Scholar
  9. 9.
    Zhao, B., Xing, E.P.: Bitam: bilingual topic admixture models for word alignment. In: COLING-ACL (2006)Google Scholar
  10. 10.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. (2003)Google Scholar
  11. 11.
    Blei, D.M., Jordan, M.I.: Modeling annotated data. In: SIGIR (2003)Google Scholar
  12. 12.
    Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Belongie, S., Perona, P.: Caltech-UCSD Birds 200. Technical Report CNS-TR-2010-001, California Institute of Technology (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Subhransu Maji
    • 1
  1. 1.Toyota Technological Institute at ChicagoChicagoUSA

Personalised recommendations