Abstract
In view of the fact that the current networks mostly improve the network performance and robustness by proposing multiple strategies to update the network parameters, this paper puts forward a novel task-driven transformed network idea. With optimizing network parameters, the network structure can be optimized by vertical update, horizontal update and cross update based on the flat network only containing the input layer and the output layer. A multi-branch error back-propagation mechanism is proposed to match the unfixed network on purpose, which is beneficial to explore the function of each hidden layer and flexible to train the network, ensuring optimal network structure for each update. Objective contribution evaluation indicators based on the tasks are also established to analyze the contribution of each strategy to the network performance and guide the subsequent network structure update. Extensive simulation results show that the method proposed is feasible, specially, the recognition accuracy of testing obtains fine results and the network training of speed is real-time on one-dimension and two-dimension image datasets.
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
Li, H., Suen, C.Y.: Robust face recognition based on dynamic rank representation. Pattern Recogn. 60(12), 13–24 (2016)
Li, H., Zhou, Z., Li, C., Zhang, S.: RCCM: reinforce cycle cascade model for image recognition. IEEE Access 8, 15369–15376 (2020)
Pan, S., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Yosinski, J., Clune, J., Bengio, Y., Lipson H.: How transferable are features in deep neural networks? In: 28th Conference on Neural Information Processing Systems, NIPS, La Jolla, California, USA, pp. 3320–3328 (2014)
Zhao, B., Huang, B., Zhong, Y.: Transfer learning with fully pretrained deep convolution networks for land-use classification. IEEE Geosci. Remote Sens. Lett. 14(9), 1436–1440 (2017)
Fang, X., Teng, S., Lai, Z., He, Z.: Robust latent subspace learning for image classification. IEEE Trans. Neural Netw. Learn. Syst. 29(6), 2502–2515 (2018)
Tollenaere, T.: SuperSAB: fast adaptive back propagation with good scaling properties. Neural Network 3(5), 561–573 (1990)
Zhang, L., Wu, K., Zhong, Y., Li, P.: A new sub-pixel mapping algorithm based on a BP neural network with an observation model. Neurocomputing 71(10), 2046–2054 (2008)
Rehman, Y.A.U., Po, L.M., Liu, M.Y.: SLNet: stereo face liveness detection via dynamic disparity-maps and convolutional neural network. Expert Syst. Appl. 142(35), 325–331 (2020)
Zeng, L., Tian, X.: Accelerating convolutional neural networks by removing interspatial and interkernel redundancies. IEEE Trans. Cybern. 50(2), 452–464 (2020)
Blake, C.L., Merz, C.J.: UCI repository of machine learning databases. Preprint at http://archive.ics.uci.edu/ml/datasets.html
Samaria, F.S., Harter, A.C.: Parameterisation of a stochastic model for human face identification. In: IEEE Workshop on Application of Computer Vision, Sarasota, USA, pp. 138–142. IEEE (1994)
Lee, K.C., Ho, J., Kriegman, D.J.: Acquiring linear subspaces for face recognition under variable lighting. IEEE Trans. Pattern Anal. Mach. Intell. 27(5), 684–698 (2005)
LeCun, Y., Huang, F.J., Bottou, L.: Learning methods for generic object recognition with invariance to pose and lighting. In: 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washing, D.C., USA, pp. II-92–II-104. IEEE (2004)
Han, X., Kashif, R., Roland, V.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)
Takagi, T., Sugeno, M.: Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. System Man Cybern. SMC-15(1), 387–403 (1985)
Acknowledgment
This work is supported by National Natural Science Foundation of China (NO. 61871241, NO. 61976120); Ministry of education cooperation in production and education (NO. 201802302115); Educational Science Research Subject of China Transportation Education Research Association (Jiaotong Education Research 1802-118); the Science and Technology Program of Nantong (JC2018025, JC2018129); Nantong University-Nantong Joint Research Center for Intelligent Information Technology (KFKT2017B04); Nanjing University State Key Lab. for Novel Software Technology (KFKT2019B15); Postgraduate Research and Practice Innovation Program of Jiangsu Province (KYCX19_2056).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, H., Zhou, Z., Li, C., Wang, Q. (2020). Transformed Network Based on Task-Driven. In: Lu, Y., Vincent, N., Yuen, P.C., Zheng, WS., Cheriet, F., Suen, C.Y. (eds) Pattern Recognition and Artificial Intelligence. ICPRAI 2020. Lecture Notes in Computer Science(), vol 12068. Springer, Cham. https://doi.org/10.1007/978-3-030-59830-3_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-59830-3_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59829-7
Online ISBN: 978-3-030-59830-3
eBook Packages: Computer ScienceComputer Science (R0)