Abstract
Deep convolutional neural network (ConvNet) is applied to versatile image recognition tasks with great success, though demanding high computation cost. Toward efficient computation, we propose a simple ConvNet architecture based on local descriptors in the bag-of-features framework. The local descriptors are formulated in a simple form of MLP and thus are efficiently computed on various ROI in a flexible manner. The proposed method is effectively trained in an end-to-end manner by reformulating the MLP descriptor into the form of deep ConvNet stacking convolution layers linearly. Through projection-based visual word encoding, the local descriptors are aggregated and fed into a classifier for image recognition tasks, which enables us to compute the network forwarding pass by matrix-vector multiplication. In the experiments on image classification, the proposed method is analyzed thoroughly, exhibiting favorable generalization performance on various tasks.
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
The PASCAL Visual Object Classes Challenge 2007 (VOC2007). http://www.pascal-network.org/challenges/VOC/voc2007/index.html
Arandjelović, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: CVPR (2016)
Azizpour, H., Razavian, A.S., Sullivan, J., Maki, A., Carlsson, S.: Factors of transferability for a generic convnet representation. PAMI 38(9), 1790–1802 (2016)
Bracewell, R.N.: The Fourier Transform and Its Applications. McGraw-Hill, New York (1999)
Cimpoi, M., Maji, S., Vedaldi, A.: Deep filter banks for texture recognition and segmentation. In: CVPR, pp. 3828–3836 (2015)
Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset. Technical report 7694, Caltech (2007)
Kawaguchi, K.: Deep learning without poor local minima. In: NIPS, pp. 586–594 (2016)
Kestur, S., Davis, J.D., Chung, E.S.: Towards a universal FPGA matrix-vector multiplication architecture. In: FCCM, pp. 9–16 (2012)
Kobayashi, T.: Dirichlet-based histogram feature transform for image classification. In: CVPR, pp. 3278–3285 (2014)
Kobayashi, T.: Analyzing filters toward efficient convnets. In: CVPR, pp. 5619–5628 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Li, L.J., Fei-Fei, L.: What, where and who? Classifying events by scene and object recognition. In: ICCV (2007)
Lin, M., Chen, Q., Yan, S.: Network in network. In: ICLR (2014)
Lowe, D.G.: Distinctive image features from scale invariant features. IJCV 60, 91–110 (2004)
Mohedano, E., McGuinness, K., O’Connor, N.E., Salvador, A., Marques, F., Giro-i-Nieto, X.: Bags of local convolutional features for scalable instance search. In: ICMR, pp. 327–331 (2016)
Nair, V., Hinton, G.: Rectified linear units improve restricted Boltzmann machines. In: ICML, pp. 807–814 (2010)
Paulin, M., Douze, M., Harchaoui, Z., Mairal, J., Perronnin, F., Schmid, C.: Local convolutional features with unsupervised training for image retrieval. In: ICCV, pp. 91–99 (2015)
Perronnin, F., Larlus, D.: Fisher vectors meet neural networks: a hybrid classification architecture. In: CVPR, pp. 3743–3752 (2015)
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: CVPR, pp. 77–85 (2017)
Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: CVPR, pp. 413–420 (2009)
Sánchez, J., Perronnin, F., Mensink, T., Verbeek, J.: Image classification with the fisher vector: theory and practice. IJCV 105(3), 222–245 (2013)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNETV2: inverted residuals and linear bottlenecks. In: CVPR, pp. 4510–4520 (2018)
Sharan, L., Rosenholtz, R., Adelson, E.: Material perception: what can you see in a brief glance? J. Vis. 9(8), 784 (2009)
Simo-Serra, E., Trulls, E., Ferraz, L., Kokkinos, I., Fua, P., Moreno-Noguer, F.: Discriminative learning of deep convolutional feature point descriptors. In: ICCV, pp. 118–126 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)
Vedaldi, A., Lenc, K.: MatConvNet - convolutional neural networks for MATLAB. In: ACM MM (2015)
Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: CVPR (2010)
Zhang, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: CVPR, pp. 6848–6856 (2018)
Zheng, L., Yang, Y., Tian, Q.: SIFT meets CNN: a decade survey of instance retrieval. PAMI 40(5), 1224–1244 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Kobayashi, T., Ide, H., Watanabe, K. (2019). Simple ConvNet Based on Bag of MLP-Based Local Descriptors. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1142. Springer, Cham. https://doi.org/10.1007/978-3-030-36808-1_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-36808-1_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36807-4
Online ISBN: 978-3-030-36808-1
eBook Packages: Computer ScienceComputer Science (R0)