Unsupervised Learning of Discriminative Relative Visual Attributes

  • Shugao Ma
  • Stan Sclaroff
  • Nazli Ikizler-Cinbis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7585)


Unsupervised learning of relative visual attributes is important because it is often infeasible for a human annotator to predefine and manually label all the relative attributes in large datasets. We propose a method for learning relative visual attributes given a set of images for each training class. The method is unsupervised in the sense that it does not require a set of predefined attributes. We formulate the learning as a mixed-integer programming problem and propose an efficient algorithm to solve it approximately. Experiments show that the learned attributes can provide good generalization and tend to be more discriminative than hand-labeled relative attributes. While in the unsupervised setting the learned attributes do not have explicit names, many are highly correlated with human annotated attributes and this demonstrates that our method is able to discover relative attributes automatically.


Relative Attribute Unsupervised Learn Visual Attribute Training Class Dimensionality Reduction Technique 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: CVPR (2009)Google Scholar
  2. 2.
    Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.A.: Describing objects by their attributes. In: CVPR (2009)Google Scholar
  3. 3.
    Farhadi, A., Endres, I., Hoiem, D.: Attribute-centric recognition for cross-category generalization. In: CVPR (2010)Google Scholar
  4. 4.
    Kumar, N., Berg, A.C., Belhumeur, P.N., Nayar, S.K.: Attribute and simile classifiers for face verification. In: ICCV (2009)Google Scholar
  5. 5.
    Parikh, D., Grauman, K.: Relative attributes. In: ICCV (2011)Google Scholar
  6. 6.
    Mahajan, D.K., Sellamanickam, S., Nair, V.: A joint learning framework for attribute models and object descriptions. In: ICCV (2011)Google Scholar
  7. 7.
    Wang, Y., Mori, G.: A Discriminative Latent Model of Object Classes and Attributes. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 155–168. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  8. 8.
    Yu, X., Aloimonos, Y.: Attribute-Based Transfer Learning for Object Categorization with Zero/One Training Example. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 127–140. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  9. 9.
    Wang, G., Forsyth, D.A.: Joint learning of visual attributes, object classes and visual saliency. In: ICCV (2009)Google Scholar
  10. 10.
    Ferrari, V., Zisserman, A.: Learning visual attributes. In: NIPS (2007)Google Scholar
  11. 11.
    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
  12. 12.
    Rohrbach, M., Stark, M., Szarvas, G., Gurevych, I., Schiele, B.: What helps where - and why? semantic relatedness for knowledge transfer. In: CVPR (2010)Google Scholar
  13. 13.
    Parikh, D., Grauman, K.: Interactively building a discriminative vocabulary of nameable attributes. In: CVPR (2011)Google Scholar
  14. 14.
    Kovashka, A., Vijayanarasimhan, S., Grauman, K.: Actively selecting annotations among objects and attributes. In: ICCV (2011)Google Scholar
  15. 15.
    Torresani, L., Szummer, M., Fitzgibbon, A.: Efficient Object Category Recognition Using Classemes. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 776–789. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  16. 16.
    Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: LIBLINEAR: A library for large linear classification. JMLR 9 (2008)Google Scholar
  17. 17.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV 42(3) (2001)Google Scholar
  18. 18.
    Chang, C.C., Lin, C.J.: LIBSVM: A library for support vector machines. ACM TIST 2, 27:1–27:27 (2011), Software available at

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Shugao Ma
    • 1
  • Stan Sclaroff
    • 1
  • Nazli Ikizler-Cinbis
    • 2
  1. 1.Department of Computer ScienceBoston UniversityUSA
  2. 2.Department of Computer EngineeringHacettepe UniversityTurkey

Personalised recommendations