Skip to main content
SpringerLink
Log in

Efficient On-the-fly Category Retrieval Using ConvNets and GPUs

  • Conference paper
  • First Online:
Book cover Computer Vision – ACCV 2014 (ACCV 2014)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 9003))

Included in the following conference series:

Abstract

We investigate the gains in precision and speed, that can be obtained by using Convolutional Networks (ConvNets) for on-the-fly retrieval – where classifiers are learnt at run time for a textual query from downloaded images, and used to rank large image or video datasets.

We make three contributions: (i) we present an evaluation of state-of-the-art image representations for object category retrieval over standard benchmark datasets containing 1M+ images; (ii) we show that ConvNets can be used to obtain features which are incredibly performant, and yet much lower dimensional than previous state-of-the-art image representations, and that their dimensionality can be reduced further without loss in performance by compression using product quantization or binarization. Consequently, features with the state-of-the-art performance on large-scale datasets of millions of images can fit in the memory of even a commodity GPU card; (iii) we show that an SVM classifier can be learnt within a ConvNet framework on a GPU in parallel with downloading the new training images, allowing for a continuous refinement of the model as more images become available, and simultaneous training and ranking. The outcome is an on-the-fly system that significantly outperforms its predecessors in terms of: precision of retrieval, memory requirements, and speed, facilitating accurate on-the-fly learning and ranking in under a second on a single GPU.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    http://arxiv.org/abs/1407.4764/.

  2. 2.

    The prevalence of the PASCAL VOC classes ‘people’, ‘cats’ and ‘birds’ in the MIRFLICKR-1M data explains why we exclude them, as restricting the annotation of these classes to reasonable levels proved to be impossible.

  3. 3.

    Miscellanea, random selection, photo random selection, random objects, random things, nothing in particular, photos of stuff, random photos, random stuff, things.

  4. 4.

    http://www.robots.ox.ac.uk/~vgg/software/deep_eval/.

References

  1. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: Proceedings of CVPR (2009)

    Google Scholar 

  2. Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. CoRR abs/1212.0402 (2012)

    Google Scholar 

  3. Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in videos. In: Proceedings of ICCV, vol. 2, pp. 1470–1477 (2003)

    Google Scholar 

  4. Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: Proceedings of CVPR, pp. 2161–2168 (2006)

    Google Scholar 

  5. Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: Proceedings of CVPR (2007)

    Google Scholar 

  6. Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 304–317. Springer, Heidelberg (2008)

    Chapter  Google Scholar 

  7. Jégou, H., Douze, M., Schmid, C., Pérez, P.: Aggregating local descriptors into a compact image representation. In: Proceedings of CVPR (2010)

    Google Scholar 

  8. Chatfield, K., Zisserman, A.: VISOR: towards on-the-fly large-scale object category retrieval. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part II. LNCS, vol. 7725, pp. 432–446. Springer, Heidelberg (2013)

    Chapter  Google Scholar 

  9. Fernando, B., Tuytelaars, T.: Mining multiple queries for image retrieval: on-the-fly learning of an object-specific mid-level representation. In: Proceedings of ICCV (2013)

    Google Scholar 

  10. Liu, Y., Xu, D., Tsang, I.W., Luo, J.: Using large-scale web data to facilitate textual query based retrieval of consumer photos. In: Proceedings of the 17th ACM International Conference on Multimedia, MM 2009, pp. 55–64 (2009)

    Google Scholar 

  11. Parkhi, O.M., Vedaldi, A., Zisserman, A.: On-the-fly specific person retrieval. In: International Workshop on Image Analysis for Multimedia Interactive Services. IEEE (2012)

    Google Scholar 

  12. Chatfield, K., Lempitsky, V., Vedaldi, A., Zisserman, A.: The devil is in the details: an evaluation of recent feature encoding methods. In: Proceedings of BMVC (2011)

    Google Scholar 

  13. 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)

    Chapter  Google Scholar 

  14. Perronnin, F., Akata, Z., Harchaoui, Z., Schmid, C.: Towards good practice in large-scale learning for image classification. In: Proceedings of CVPR, pp. 3482–3489 (2012)

    Google Scholar 

  15. Jégou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE PAMI 33(1), 117–128 (2011)

    Article  Google Scholar 

  16. Torralba, A., Fergus, R., Freeman, W.T.: 80 million tiny images: a large dataset for non-parametric object and scene recognition. IEEE PAMI 30, 1958–1970 (2008)

    Article  Google Scholar 

  17. Raginsky, M., Lazebnik, S.: Locality sensitive binary codes from shift-invariant kernels. In: NIPS (2009)

    Google Scholar 

  18. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)

    Article  Google Scholar 

  19. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2012)

    Google Scholar 

  20. Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. CoRR abs/1311.2901 (2013)

    Google Scholar 

  21. Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. In: Proceedings of BMVC (2014)

    Google Scholar 

  22. 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)

    Article  Google Scholar 

  23. Huiskes, M.J., Lew, M.S.: The MIR flickr retrieval evaluation. In: MIR 2008: Proceedings of the 2008 ACM International Conference on Multimedia Information Retrieval (2008)

    Google Scholar 

  24. Huiskes, M.J., Thomee, B., Lew, M.S.: New trends and ideas in visual concept detection: the MIR flickr retrieval evaluation initiative. In: MIR 2010: Proceedings of the 2010 ACM International Conference on Multimedia Information Retrieval, pp. 527–536 (2010)

    Google Scholar 

  25. Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: DeCAF: a deep convolutional activation feature for generic visual recognition. CoRR abs/1310.1531 (2013)

    Google Scholar 

  26. Razavian, A., Azizpour, H., Sullivan, J., Carlsson, S.: CNN Features off-the-shelf: an Astounding Baseline for Recognition. CoRR abs/1403.6382 (2014)

    Google Scholar 

  27. Sánchez, J., Perronnin, F.: High-dimensional signature compression for large-scale image classification. In: Proceedings of CVPR (2011)

    Google Scholar 

  28. Jégou, H., Furon, T., Fuchs, J.J.: Anti-sparse coding for approximate nearest neighbor search. In: Proceedings of ICASSP, pp. 2029–2032 (2012)

    Google Scholar 

  29. Simonyan, K., Vedaldi, A., Zisserman, A.: Learning local feature descriptors using convex optimisation. IEEE PAMI 36, 1573–1585 (2014)

    Article  Google Scholar 

  30. Parkhi, O.M., Simonyan, K., Vedaldi, A., Zisserman, A.: A compact and discriminative face track descriptor. In: Proceedings of CVPR. IEEE (2014)

    Google Scholar 

  31. Arandjelović, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: Proceedings of CVPR (2012)

    Google Scholar 

  32. Sánchez, J., Perronnin, F., Emídio de Campos, T.: Modeling the spatial layout of images beyond spatial pyramids. Pattern Recogn. Lett. 33, 2216–2223 (2012)

    Article  Google Scholar 

  33. Arandjelović, R., Zisserman, A.: All about VLAD. In: Proceedings of CVPR (2013)

    Google Scholar 

  34. Jia, Y.: Caffe: an open source convolutional architecture for fast feature embedding (2013). http://caffe.berkeleyvision.org/

  35. Shalev-Shwartz, S., Singer, Y., Srebro, N.: Pegasos: primal estimated sub-gradient SOlver for SVM. In: Proceedings of ICML, vol. 227 (2007)

    Google Scholar 

Download references

Acknowledgements

This work was supported by the EPSRC and ERC grant VisRec no. 228180. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the GPUs used for this research.

Author information

Authors and Affiliations

  1. Department of Engineering Science, University of Oxford, Oxford, UK

    Ken Chatfield, Karen Simonyan & Andrew Zisserman

Authors
  1. Ken Chatfield
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Karen Simonyan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Andrew Zisserman
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ken Chatfield .

Editor information

Editors and Affiliations

  1. Technische Universität München, Garching, Bayern, Germany

    Daniel Cremers

  2. University of Adelaide, Adelaide, South Australia, Australia

    Ian Reid

  3. Keio University, Yokohama, Kanagawa, Japan

    Hideo Saito

  4. University of California at Merced, Merced, California, USA

    Ming-Hsuan Yang

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Chatfield, K., Simonyan, K., Zisserman, A. (2015). Efficient On-the-fly Category Retrieval Using ConvNets and GPUs. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision – ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9003. Springer, Cham. https://doi.org/10.1007/978-3-319-16865-4_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-16865-4_9

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-16864-7

  • Online ISBN: 978-3-319-16865-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation