Advertisement

Attributes for Classifier Feedback

  • Amar Parkash
  • Devi Parikh
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7574)

Abstract

Traditional active learning allows a (machine) learner to query the (human) teacher for labels on examples it finds confusing. The teacher then provides a label for only that instance. This is quite restrictive. In this paper, we propose a learning paradigm in which the learner communicates its belief (i.e. predicted label) about the actively chosen example to the teacher. The teacher then confirms or rejects the predicted label. More importantly, if rejected, the teacher communicates an explanation for why the learner’s belief was wrong. This explanation allows the learner to propagate the feedback provided by the teacher to many unlabeled images. This allows a classifier to better learn from its mistakes, leading to accelerated discriminative learning of visual concepts even with few labeled images. In order for such communication to be feasible, it is crucial to have a language that both the human supervisor and the machine learner understand. Attributes provide precisely this channel. They are human-interpretable mid-level visual concepts shareable across categories e.g. “furry”, “spacious”, etc. We advocate the use of attributes for a supervisor to provide feedback to a classifier and directly communicate his knowledge of the world. We employ a straightforward approach to incorporate this feedback in the classifier, and demonstrate its power on a variety of visual recognition scenarios such as image classification and annotation. This application of attributes for providing classifiers feedback is very powerful, and has not been explored in the community. It introduces a new mode of supervision, and opens up several avenues for future research.

Keywords

Query Image Category Label Attribute Predictor Large Vocab Visual Concept 
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.
    Smith, J., Naphade, M., Natsev, A.: Multimedia semantic indexing using model vectors. In: ICME (2003)Google Scholar
  2. 2.
    Rasiwasia, N., Moreno, P., Vasconcelos, N.: Bridging the gap: Query by semantic example. IEEE Transactions on Multimedia (2007)Google Scholar
  3. 3.
    Naphade, M., Smith, J., Tesic, J., Chang, S., Hsu, W., Kennedy, L., Hauptmann, A., Curtis, J.: Large-scale concept ontology for multimedia. IEEE Multimedia (2006)Google Scholar
  4. 4.
    Zavesky, E., Chang, S.F.: Cuzero: Embracing the frontier of interactive visual search for informed users. In: Proceedings of ACM Multimedia Information Retrieval (2008)Google Scholar
  5. 5.
    Douze, M., Ramisa, A., Schmid, C.: Combining attributes and fisher vectors for efficient image retrieval. In: CVPR (2011)Google Scholar
  6. 6.
    Wang, X., Liu, K., Tang, X.: Query-specific visual semantic spaces for web image re-ranking. In: CVPR (2011)Google Scholar
  7. 7.
    Lampert, C., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: CVPR (2009)Google Scholar
  8. 8.
    Parikh, D., Grauman, K.: Relative attributes. In: ICCV (2011)Google Scholar
  9. 9.
    Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR (2009)Google Scholar
  10. 10.
    Kumar, N., Berg, A., Belhumeur, P., Nayar, S.: Attribute and simile classifiers for face verification. In: ICCV (2009)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.
    Wang, J., Markert, K., Everingham, M.: Learning models for object recognition from natural language descriptions. In: BMVC (2009)Google Scholar
  13. 13.
    Wang, G., Forsyth, D.: Joint learning of visual attributes, object classes and visual saliency. In: ICCV (2009)Google Scholar
  14. 14.
    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
  15. 15.
    Ferrari, V., Zisserman, A.: Learning visual attributes. In: NIPS (2007)Google Scholar
  16. 16.
    Branson, S., Wah, C., Schroff, F., Babenko, B., Welinder, P., Perona, P., Belongie, S.: Visual Recognition with Humans in the Loop. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 438–451. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  17. 17.
    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
  18. 18.
    Wang, G., Forsyth, D., Hoiem, D.: Comparative object similarity for improved recognition with few or no examples. In: CVPR (2010)Google Scholar
  19. 19.
    Mahajan, D., Sellamanickam, S., Nair, V.: A joint learning framework for attribute models and object descriptions. In: ICCV (2011)Google Scholar
  20. 20.
    Kovashka, A., Vijayanarasimhan, S., Grauman, K.: Actively selecting annotations among objects and attributes. In: ICCV (2011)Google Scholar
  21. 21.
    Wah, C., Branson, S., Perona, P., Belongie, S.: Multiclass recognition and part localization with humans in the loop. In: ICCV (2011)Google Scholar
  22. 22.
    Branson, S., Wah, C., Schroff, F., Babenko, B., Welinder, P., Perona, P., Belongie, S.: Visual Recognition with Humans in the Loop. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 438–451. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  23. 23.
    Parikh, D., Grauman, K.: Interactively building a discriminative vocabulary of nameable attributes. In: CVPR (2011)Google Scholar
  24. 24.
    Bourdev, L., Maji, S., Malik, J.: Describing people: A poselet-based approach to attribute classification. In: ICCV (2011)Google Scholar
  25. 25.
    Russel, B., Torralba, A., Murphy, K., Freeman, W.: Labelme: a database and web-based tool for image annotation. IJCV (2008)Google Scholar
  26. 26.
    Farhadi, A., Endres, I., Hoiem, D.: Attribute-centric recognition for cross-category generalization. In: CVPR (2010)Google Scholar
  27. 27.
    Bourdev, L., Malik, J.: Poselets: Body part detectors trained using 3d human pose annotations. In: ICCV (2009)Google Scholar
  28. 28.
    Vijayanarasimhan, S., Grauman, K.: Multi-level active prediction of useful image annotations for recognition. In: NIPS (2008)Google Scholar
  29. 29.
    Siddiquie, B., Gupta, A.: Beyond active noun tagging: Modeling contextual interactions for multi-class active learning. In: CVPR (2010)Google Scholar
  30. 30.
    Raghavan, H., Madani, O., Jones, R.: Interactive feature selection. IJCAI (2005)Google Scholar
  31. 31.
    Druck, G., Settles, B., McCallum, A.: Active learning by labeling features. In: EMNLP (2009)Google Scholar
  32. 32.
    Zaidan, O., Eisner, J., Piatko, C.: Using annotator rationales to improve machine learning for text categorization. In: NAACL - HLT (2007)Google Scholar
  33. 33.
    Donahue, J., Grauman, K.: Annotator rationales for visual recognition. In: ICCV (2011)Google Scholar
  34. 34.
    Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. PAMI (2010)Google Scholar
  35. 35.
    Golland, P.: Discriminative direction for kernel classifiers. In: NIPS (2001)Google Scholar
  36. 36.
    Shrivastava, A., Singh, S., Gupta, A.: Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 370–384. Springer, Heidelberg (2012)Google Scholar
  37. 37.
    Joachims, T.: Optimizing search engines using clickthrough data. In: KDD (2002)Google Scholar
  38. 38.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: A Large-Scale Hierarchical Image Database. In: CVPR 2009 (2009)Google Scholar
  39. 39.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Amar Parkash
    • 1
  • Devi Parikh
    • 2
  1. 1.Indraprastha Institute of Information TechnologyDelhiIndia
  2. 2.Toyota Technological InstituteChicagoUS

Personalised recommendations