Abstract
In recent years, deep learning has attracted much interest for addressing complex AI tasks. However, most of the deep learning models need to be trained for a long time in order to obtain good results. To overcome this problem, the deep convolutional activation feature (DeCAF) was proposed, which is directly extracted from the activation of a well trained deep convolutional neural network. Nevertheless, the dimensionality of DeCAF is simply fixed to a constant number. In this case, one may ask whether DeCAF is good enough for image classification applications and whether we can further improve its performance? To answer these two questions, we propose a new model called RS-DeCAF based on “reducing” and “stretching” the dimensionality of DeCAF. In the implementation of RS-DeCAF, we reduce the dimensionality of DeCAF using dimensionality reduction methods, such as PCA, and meanwhile increase the dimensionality by stretching the weight matrix between successive layers. RS-DeCAF is aimed to discover the effective representations of data for classification tasks. As there is no back propagation is needed for network training, RS-DeCAF is very efficient and can be easily applied to large scale problems. Extensive experiments on image classification show that RS-DeCAF not only slightly improves DeCAF, but dramatically outperforms previous “stretching” and other state-of-the-art approaches. Hence, RS-DeCAF can be considered as an effective substitute for previous DeCAF and “stretching” approaches.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems, pp. 1097–1105 (2012)
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzen, E., Darrel, T.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: The Internalational Compouter Machine Learning, pp. 647–655 (2014)
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the ACM International Conference on Multimedia, pp. 675–678. ACM (2013). http://caffe.berkeleyvision.org
Tsang, I., Kowk, J., Cheung, P.-M.: Core vector machines: fast SVM training on very large data sets. J. Mach. Learn. Res. 6(2), 363–392 (2005)
Lin, M., Chen, Q., Yan, S.: Network in network, J. CoRR (2013). abs/1312.4400
Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: Neural Information Processing Systems, pp. 1988–1996 (2014)
Zheng, Y., Zhong, G., Liu, J., Cai, X., Dong, J.: Visual texture perception with feature learning models and deep architectures. In: Li, S., Liu, C., Wang, Y. (eds.) CCPR 2014, Part I. CCIS, vol. 483, pp. 401–410. Springer, Heidelberg (2014)
Wang, N., Yeung, D.Y.: Ensemble-based tracking: aggregating crowdsourced structured time series data. In: Proceedings of the 31st International Conference on Machine Learning (ICML-14), pp. 1107–1115 (2014)
Pandey, G., Dukkipati, A.: Learning by stretching deep networks. In: Proceedings of the 31st International Conference on Machine Learning (ICML-14), pp. 1719–1727 (2014)
LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. J. Neural Comput. 1(4), 541–551 (1989)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. J. Proc. IEEE 86(11), 2278–2324 (1998)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Computer Vision and Pattern Recognition, pp. 248–255 (2009)
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks (2013). arXiv preprint arXiv:1312.6229
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Rabinovich, A.: Going deeper with convolutions (2014)
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Fei-Fei, L.: Imagenet large scale visual recognition challenge (2014)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 818–833. Springer, Heidelberg (2014)
Jolliffe, I.: Principal Component Analysis. Wiley, New York (2002)
Fisher, R.A.: The use of multiple measurements in taxonomic problems. J. Ann. Eugenics 7(2), 179–188 (1936)
Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. J. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 594–611 (2006)
Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Belongie, S., Perona, P.: Caltech-UCSD Birds 200 (2010)
Coates, A., Ng, A.Y., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. Int. Conf. Artif. Intell. Stat. 15, 215–223 (2011)
Hinton, G., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. J. Neural Comput. 18(7), 1527–1554 (2006)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. J. Sci. 313(5786), 504–507 (2006)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors (2012). arXiv preprint arXiv:1207.0580
Scholkopf, B., Smola, A., Mller, K.R.: Nonlinear component analysis as a kernel eigenvalue problem. J. Neural Comput. 10(5), 1299–1319 (1998)
Baudat, G., Anouar, F.: Generalized discriminant analysis using a kernel approach. J. Neural Comput. 12(10), 2385–2404 (2000)
Dosovitskiy, A., Springenberg, J.T., Riedmiller, M., Brox, T.: Discriminative unsupervised feature learning with convolutional neural networks. In: Neural Information Processing Systems, pp. 766–774 (2014)
Scholkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT press, Cambridge (2002)
Vapnik, V.N., Vapnik, V.: Statistical Learning Theory, vol. 1. Wiley, New York (1998)
Swersky, K., Snoek, J., Adams, R.P.: Multi-task bayesian optimization. In: Neural Information Processing Systems, pp. 2004–2012 (2013)
Cho, Y., Saul, L.K.: Large-margin classification in infinite neural networks. J. Neural Comput. 22(10), 2678–2697 (2010)
Acknowledgments
This work was supported by the National Basic Research Program of China (No. 2012CB316301), the National Natural Science Foundation of China (No. 61271405, No. 61403353, No. 61473236 and No. 61401413), the Ph.D. Program Foundation Of Ministry Of Education Of China (No. 20120132110018), the Open Project Program of the National Laboratory of Pattern Recognition (NLPR) and the Fundamental Research Funds for the Central Universities of China.
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
Cai, Y., Zhong, G., Zheng, Y., Huang, K., Dong, J. (2015). Is DeCAF Good Enough for Accurate Image Classification?. In: Arik, S., Huang, T., Lai, W., Liu, Q. (eds) Neural Information Processing. ICONIP 2015. Lecture Notes in Computer Science(), vol 9490. Springer, Cham. https://doi.org/10.1007/978-3-319-26535-3_41
Download citation
DOI: https://doi.org/10.1007/978-3-319-26535-3_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26534-6
Online ISBN: 978-3-319-26535-3
eBook Packages: Computer ScienceComputer Science (R0)