Advertisement

Negative Evidences and Co-occurences in Image Retrieval: The Benefit of PCA and Whitening

  • Hervé Jégou
  • Ondřej Chum
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7573)

Abstract

The paper addresses large scale image retrieval with short vector representations. We study dimensionality reduction by Principal Component Analysis (PCA) and propose improvements to its different phases. We show and explicitly exploit relations between i) mean subtraction and the negative evidence, i.e., a visual word that is mutually missing in two descriptions being compared, and ii) the axis de-correlation and the co-occurrences phenomenon. Finally, we propose an effective way to alleviate the quantization artifacts through a joint dimensionality reduction of multiple vocabularies. The proposed techniques are simple, yet significantly and consistently improve over the state of the art on compact image representations. Complementary experiments in image classification show that the methods are generally applicable.

Keywords

Dimensionality Reduction Image Retrieval Visual Word Query Image Local Descriptor 
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.
    Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos. In: ICCV (2003)Google Scholar
  2. 2.
    Nistér, D., Stewénius, H.: Scalable recognition with a vocabulary tree. In: CVPR, pp. 2161–2168 (2006)Google Scholar
  3. 3.
    Chum, O., Philbin, J., Sivic, J., Isard, M., Zisserman, A.: Total recall: Automatic query expansion with a generative feature model for object retrieval. In: ICCV (2007)Google Scholar
  4. 4.
    Jégou, H., Douze, M., Schmid, C.: Improving bag-of-features for large scale image search. IJCV 87, 316–336 (2010)CrossRefGoogle Scholar
  5. 5.
    Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: ECCV Workshop Statistical Learning in Computer Vision (2004)Google Scholar
  6. 6.
    Torralba, A., Fergus, R., Weiss, Y.: Small codes and large databases for recognition. In: CVPR (2008)Google Scholar
  7. 7.
    Perronnin, F., Liu, Y., Sanchez, J., Poirier, H.: Large-scale image retrieval with compressed Fisher vectors. In: CVPR (2010)Google Scholar
  8. 8.
    Jégou, H., Douze, M., Schmid, C., Pérez, P.: Aggregating local descriptors into a compact image representation. In: CVPR (2010)Google Scholar
  9. 9.
    Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: NIPS (2008)Google Scholar
  10. 10.
    Jégou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. Trans. PAMI 33, 117–128 (2011)CrossRefGoogle Scholar
  11. 11.
    Perronnin, F., Dance, C.R.: Fisher kernels on visual vocabularies for image categorization. In: CVPR (2007)Google Scholar
  12. 12.
    Perronnin, F., Sánchez, J., Mensink, T.: Improving the Fisher Kernel for Large-Scale Image Classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 143–156. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  13. 13.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. IJCV 42, 145–175 (2001)zbMATHCrossRefGoogle Scholar
  14. 14.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer (2007)Google Scholar
  15. 15.
    Jégou, H., Schmid, C., Harzallah, H., Verbeek, J.: Accurate image search using the contextual dissimilarity measure. Trans. PAMI 32, 2–11 (2010)CrossRefGoogle Scholar
  16. 16.
    Matas, J., Chum, O., Martin, U., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: BMVC, pp. 384–393 (2002)Google Scholar
  17. 17.
    Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. IJCV 60, 63–86 (2004)CrossRefGoogle Scholar
  18. 18.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  19. 19.
    Jégou, H., Perronnin, F., Douze, M., Sánchez, J., Pérez, P., Schmid, C.: Aggregating local descriptors into compact codes. In: Trans. PAMI (2012)Google Scholar
  20. 20.
    Jégou, H., Douze, M., Schmid, C.: On the burstiness of visual elements. In: CVPR (2009)Google Scholar
  21. 21.
    Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: CVPR (2007)Google Scholar
  22. 22.
    Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Lost in quantization: Improving particular object retrieval in large scale image databases. In: CVPR (2008)Google Scholar
  23. 23.
    Perdoch, M., Chum, O., Matas, J.: Efficient representation of local geometry for large scale object retrieval. In: CVPR (2009)Google Scholar
  24. 24.
    Chum, O., Matas, J.: Unsupervised discovery of co-occurrence in sparse high dimensional data. In: CVPR (2010)Google Scholar
  25. 25.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.V.: A comparison of affine region detectors. IJCV 65, 43–72 (2005)CrossRefGoogle Scholar
  26. 26.
    Comon, P.: Independent component analysis, a new concept? Signal Processing 36 (1994)Google Scholar
  27. 27.
    Grauman, K., Darrell, T.: The pyramid match kernel: Discriminative classification with sets of image features. In: ICCV (2005)Google Scholar
  28. 28.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. IJCV 88, 303–338 (2010)CrossRefGoogle Scholar
  29. 29.
    Chatfield, K., Lempitsky, V., Vedaldi, A., Zisserman, A.: The devil is in the details: an evaluation of recent feature encoding methods. In: BMVC (2011)Google Scholar
  30. 30.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Hervé Jégou
    • 1
  • Ondřej Chum
    • 2
  1. 1.INRIA RennesFrance
  2. 2.CMP, Department of Cybernetics, Faculty of EECTU in PragueCzech Republic

Personalised recommendations