International Conference on Similarity Search and Applications

Similarity Search and Applications pp 237-243 | Cite as

Efficient Image Search with Neural Net Features

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9371)

Abstract

We present an efficiency evaluation of similarity search techniques applied on visual features from deep neural networks. Our test collection consists of 20 million 4096-dimensional descriptors (320 GB of data). We test approximate \(k\)-NN search using several techniques, specifically FLANN library (a popular in-memory implementation of k-d tree forest), M-Index (that uses recursive Voronoi partitioning of a metric space), and PPP-Codes, which work with memory codes of metric objects and use disk storage for candidate refinement. Our evaluation shows that as long as the data fit in main memory, the FLANN and the M-Index have practically the same ratio between precision and response time. The PPP-Codes identify candidate sets ten times smaller then the other techniques and the response times are around 500 ms for the whole 20M dataset stored on the disk. The visual search with this index is available as an online demo application. The collection of 20M descriptors is provided as a public dataset to academic community.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Budikova, P., Batko, M., Zezula, P.: Evaluation platform for content-based image retrieval systems. In: Gradmann, S., Borri, F., Meghini, C., Schuldt, H. (eds.) TPDL 2011. LNCS, vol. 6966, pp. 130–142. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  2. 2.
    Chávez, E., Navarro, G.: Measuring the dimensionality of general metric spaces. Technical report, Department of Computer Science, University of Chile (2000)Google Scholar
  3. 3.
    Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: International Conference in Machine Learning (ICML), pp. 647–655 (2014)Google Scholar
  4. 4.
    Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: International Conference on Multimedia (2014)Google Scholar
  5. 5.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Advances In Neural Information Processing Systems 25, 1097–1105 (2012)Google Scholar
  6. 6.
    LeCun, Y., Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W., Jackel, L.: Backpropagation applied to handwritten zip code recognition. Neural Computation 1(4) (1989)Google Scholar
  7. 7.
    Muja, M., Lowe, D.G.: Scalable Nearest Neighbour Algorithms for High Dimensional Data. IEEE Trans. on PAMI 36(11), 2227–2240 (2014)CrossRefGoogle Scholar
  8. 8.
    Novak, D., Batko, M., Zezula, P.: Metric Index: An Efficient and Scalable Solution for Precise and Approximate Similarity Search. Information Systems 36(4), 721–733 (2011)CrossRefGoogle Scholar
  9. 9.
    Novak, D., Batko, M., Zezula, P.: Large-scale image retrieval using neural net descriptors. In: Proceedings of SIGIR 2015 (to appear, 2015)Google Scholar
  10. 10.
    Novak, D., Zezula, P.: Performance Study of Independent Anchor Spaces for Similarity Searching. The Computer Journal 57(11), 1741–1755 (2014)CrossRefGoogle Scholar
  11. 11.
    Novak, D., Zezula, P.: Rank aggregation of candidate sets for efficient similarity search. In: Decker, H., Lhotská, L., Link, S., Spies, M., Wagner, R.R. (eds.) DEXA 2014, Part II. LNCS, vol. 8645, pp. 42–58. Springer, Heidelberg (2014) Google Scholar
  12. 12.
    Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Learning and transferring mid-level image representations using convolutional neural networks. In: CVPR (2014)Google Scholar
  13. 13.
    Wan, J., Wang, D., Hoi, S., Wu, P., Zhu, J., Zhang, Y., Li, J.: Deep learning for content-based image retrieval: a comprehensive study. In: Proc. of 22nd ACM International Conference on Multimedia (2014)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Masaryk UniversityBrnoCzech Republic
  2. 2.Czech Technical UniversityPragueCzech Republic

Personalised recommendations