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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 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.
Miscellanea, random selection, photo random selection, random objects, random things, nothing in particular, photos of stuff, random photos, random stuff, things.
- 4.
References
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)
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)
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)
Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: Proceedings of CVPR, pp. 2161–2168 (2006)
Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: Proceedings of CVPR (2007)
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)
Jégou, H., Douze, M., Schmid, C., Pérez, P.: Aggregating local descriptors into a compact image representation. In: Proceedings of CVPR (2010)
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)
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)
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)
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)
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)
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)
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)
Jégou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE PAMI 33(1), 117–128 (2011)
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)
Raginsky, M., Lazebnik, S.: Locality sensitive binary codes from shift-invariant kernels. In: NIPS (2009)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2012)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. CoRR abs/1311.2901 (2013)
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)
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)
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)
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)
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)
Razavian, A., Azizpour, H., Sullivan, J., Carlsson, S.: CNN Features off-the-shelf: an Astounding Baseline for Recognition. CoRR abs/1403.6382 (2014)
Sánchez, J., Perronnin, F.: High-dimensional signature compression for large-scale image classification. In: Proceedings of CVPR (2011)
Jégou, H., Furon, T., Fuchs, J.J.: Anti-sparse coding for approximate nearest neighbor search. In: Proceedings of ICASSP, pp. 2029–2032 (2012)
Simonyan, K., Vedaldi, A., Zisserman, A.: Learning local feature descriptors using convex optimisation. IEEE PAMI 36, 1573–1585 (2014)
Parkhi, O.M., Simonyan, K., Vedaldi, A., Zisserman, A.: A compact and discriminative face track descriptor. In: Proceedings of CVPR. IEEE (2014)
Arandjelović, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: Proceedings of CVPR (2012)
Sánchez, J., Perronnin, F., Emídio de Campos, T.: Modeling the spatial layout of images beyond spatial pyramids. Pattern Recogn. Lett. 33, 2216–2223 (2012)
Arandjelović, R., Zisserman, A.: All about VLAD. In: Proceedings of CVPR (2013)
Jia, Y.: Caffe: an open source convolutional architecture for fast feature embedding (2013). http://caffe.berkeleyvision.org/
Shalev-Shwartz, S., Singer, Y., Srebro, N.: Pegasos: primal estimated sub-gradient SOlver for SVM. In: Proceedings of ICML, vol. 227 (2007)
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
Corresponding author
Editor information
Editors and Affiliations
Rights 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)