Linear Discriminant Analysis for Zero-shot Learning Image Retrieval

Sovann EN, Frédéric Jurie, Stéphane Nicolas, Caroline Petitjean, Laurent Heutte

Abstract

This paper introduces a new distance function for comparing images in the context of content-based image retrieval. Given a query and a large dataset to be searched, the system has to provide the user – as efficiently as possible – with a list of images ranked according to their distance to the query. Because of computational issues, traditional image search systems are generally based on conventional distance function such as the Euclidian distance or the dot product, avoiding the use of any training data nor expensive online metric learning algorithms. The drawback is that, in this case, the system can hardly cope with the variability of image contents. This paper proposes a simple yet efficient zero-shot learning algorithm that can learn a query-adapted distance function from a single image (the query) or from a few images (e.g. some user-selected images in a relevance feedback iteration), hence improving the quality of the retrieved images. This allows our system to work with any object categories without requiring any training data, and is hence more applicable in real world use cases. More interestingly, our system can learn the metric on the fly, at almost no cost, and the cost of the ranking function is as low as the dot product distance. By allowing the system to learn to rank the images, significantly and consistently improved results (over the conventional approaches) have been observed on the Oxford5k, Paris6k and Holiday1k datasets.

References

  1. Deng, W., Hu, J., and Guo, J. (2014). Linear ranking analysis. In IEEE Conference on Computer Vision and Pattern Recognition, pages 3638-3645.
  2. Hoo, W. L. and Chan, C. S. (2013). Plsa-based zero-shot learning. In IEEE International Conference on Image Processing, pages 4297-4301.
  3. Jégou, H. and Chum, O. (2012). Negative evidences and co-occurences in image retrieval: The benefit of pca and whitening. In European Conference on Computer Vision, pages 774-787.
  4. Jégou, H., Perronnin, F., Douze, M., Sánchez, J., Pérez, P., and Schmid, C. (2012). Aggregating local image descriptors into compact codes. Transactions on Pattern Analysis and Machine Intelligence, 34(9):1704-1716.
  5. Kim, T.-K., Wong, K.-Y. K., Stenger, B., Kittler, J., and Cipolla, R. (2007). Incremental linear discriminant analysis using sufficient spanning set approximations. IEEE Conference on Computer Vision and Pattern Recognition, pages 1-8.
  6. Lampert, C. H., Nickisch, H., and Harmeling, S. (2009). Learning to detect unseen object classes by betweenclass attribute transfer. In IEEE Conference on Computer Vision and Pattern Recognition, pages 951-958.
  7. Larochelle, H., Erhan, D., and Bengio, Y. (2008). Zerodata learning of new tasks. In AAAI, volume 1, pages 646-651.
  8. Lu, K. and He, X. (2005). Image retrieval based on incremental subspace learning. Pattern Recognition, 38(11):2047-2054.
  9. Palatucci, M., Pomerleau, D., Hinton, G. E., and Mitchell, T. M. (2009). Zero-shot learning with semantic output codes. In Advances in neural information processing systems, pages 1410-1418.
  10. Parikh, D. and Grauman, K. (2011). Relative attributes. In IEEE International Conference on Computer Vision, pages 503-510.
  11. Perronnin, F., Liu, Y., Sánchez, J., and Poirier, H. (2010). Large-scale image retrieval with compressed fisher vectors. In Computer Vision and Pattern Recognition, pages 3384-3391.
  12. Philbin, J., Chum, O., Isard, M., Sivic, J., and Zisserman, A. (2007). Object retrieval with large vocabularies and fast spatial matching. In Conference on Computer Vision and Pattern Recognition, pages 1-8.
  13. Sánchez, J., Perronnin, F., Mensink, T., and Verbeek, J. (2013). Image classification with the Fisher vector: Theory and practice. International Journal of Computer Vision, 105(3):222-245.
  14. Sivic, J. and Zisserman, A. (2003). Video google: A text retrieval approach to object matching in videos. In International Conference on Computer Vision, pages 1470-1477.
  15. Swets, D. L. and Weng, J. J. (1996). Using discriminant eigenfeatures for image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8):831-836.
  16. Tao, D., Tang, X., Li, X., and Rui, Y. (2006). Direct kernel biased discriminant analysis: a new content-based image retrieval relevance feedback algorithm. IEEE Transactions on Multimedia, 8(4):716-727.
  17. You, D., Hamsici, O. C., and Martinez, A. M. (2011). Kernel optimization in discriminant analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(3):631-638.
  18. Zhao, M., Zhang, Z., Chow, T. W., and Li, B. (2014). Soft label based linear discriminant analysis for image recognition and retrieval. Computer Vision and Image Understanding, 121:86-99.
  19. Zhu, M. and Martinez, A. M. (2006). Subclass discriminant analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(8):1274-1286.
Download


Paper Citation


in Harvard Style

EN S., Jurie F., Nicolas S., Petitjean C. and Heutte L. (2015). Linear Discriminant Analysis for Zero-shot Learning Image Retrieval . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 70-77. DOI: 10.5220/0005300200700077


in Bibtex Style

@conference{visapp15,
author={Sovann EN and Frédéric Jurie and Stéphane Nicolas and Caroline Petitjean and Laurent Heutte},
title={Linear Discriminant Analysis for Zero-shot Learning Image Retrieval},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={70-77},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005300200700077},
isbn={978-989-758-090-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Linear Discriminant Analysis for Zero-shot Learning Image Retrieval
SN - 978-989-758-090-1
AU - EN S.
AU - Jurie F.
AU - Nicolas S.
AU - Petitjean C.
AU - Heutte L.
PY - 2015
SP - 70
EP - 77
DO - 10.5220/0005300200700077