Abstract
For most machine learning algorithms, the performance of model trained on the source domain degenerates obviously when it is applied to the target domain because the distributions of both domains are different. Besides, in many cases, there is a lack of adequate supervised target domain training samples. In order to solve the mismatch between the domains and the lack of training samples, this paper proposes jointing domain adaptation and generic learning on solving unsupervised face recognition. Firstly, samples are selected randomly from multiple source and target domains which do not contain interest subjects and construct multiple sub-datasets. Secondly, learning a common subspace for each sub-dataset. In the common subspace, source and target domains can mutual interlace and their structures are well preserved, and we can get more discrimination information from multiple feature subspaces. Finally, the recognition is obtained by using combine strategies. The experimental results show that the recognition performance of the framework is better than that of the competitive ones.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ding, Z., Zhao, H., Fu, Y.: Multi-source transfer learning. Learning Representation for Multi-View Data Analysis. AIKP, pp. 175–202. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-00734-8_8
Geng, B., Tao, D., Xu, C.: DAML: domain adaptation metric learning. IEEE Trans. Image Proces. 20(10), 2980–2989 (2011). https://doi.org/10.1109/TIP.2011.2134107
Ghosh, J.: Multiclassifier systems: back to the future. In: Roli, F., Kittler, J. (eds.) MCS 2002. LNCS, vol. 2364, pp. 1–15. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-45428-4_1
Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: an unsupervised approach. In: IEEE International Conference on Computer Vision, pp. 999–1006 (2011). https://doi.org/10.1109/ICCV.2011.6126344
Ho, T.K., Hull, J.J., Srihari, S.N.: Decision combination in multiple classifier systems. IEEE Trans. Pattern Anal. Mach. Intell. 16(1), 66–75 (1994). https://doi.org/10.1109/34.273716
Joachims, T.: Text categorization with support vector machines: learning with many relevant features. In: Nédellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398, pp. 137–142. Springer, Heidelberg (1998). https://doi.org/10.1007/BFb0026683
Kan, M., Wu, J., Shan, S., Chen, X.: Domain adaptation for face recognition: targetize source domain bridged by common subspace. Int. J. Comput. Vis., 94–109 (2013). https://doi.org/10.1007/s11263-013-0693-1
Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On combining classifiers. IEEE Trans. Pattern Anal. Mach. Intell. 20(3), 226–239 (1998). https://doi.org/10.1109/34.667881
Li, S., Liu, F., Liang, J., Cai, Z., Liang, Z.: Optimization of face recognition system based on azure IoT edge. Comput. Mater. Continua 61(3), 1377–1389 (2019)
Liu, C.L.: Classifier combination based on confidence transformation. Pattern Recogn. 38(1), 11–28 (2005). https://doi.org/10.1016/j.patcog.2004.05.013
Mansour, Y., Mohri, M., Rostamizadeh, A.: Domain adaptation with multiple sources. In: Advances in Neural Information Processing Systems, pp. 1041–1048 (2008)
Meng, Y., Lei, Z., Feng, X., Zhang, D.: Fisher discrimination dictionary learning for sparse representation. Proceedings 24(4), 543–550 (2011). https://doi.org/10.1109/ICCV.2011.6126286
Nguyen, H.V., Patel, V.M., Nasrabadi, N.M., Chellappa, R.: Sparse embedding: a framework for sparsity promoting dimensionality reduction. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 414–427. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33783-3_30
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010). https://doi.org/10.1109/TKDE.2009.191
Shawe-Taylor, J., Sun, S.: A review of optimization methodologies in support vector machines. Neurocomputing 74(17), 3609–3618 (2011). https://doi.org/10.1016/j.neucom.2011.06.026
Shekhar, S., Patel, V.M., Nguyen, H.V., Chellappa, R.: Generalized domain-adaptive dictionaries. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 361–368 (2013). https://doi.org/10.1109/CVPR.2013.53
Sinno Jialin, P., Tsang, I.W., Kwok, J.T., Qiang, Y.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22(2), 199–210 (2011). https://doi.org/10.1109/TNN.2010.2091281
Sun, S., Shi, H., Wu, Y.: A survey of multi-source domain adaptation. Inf. Fusion 24(C), 84–92 (2015). https://doi.org/10.1016/j.inffus.2014.12.003
Tang, Z., et al.: Robust image hashing via random Gabor filtering and DWT. Comput. Mater. Continua 55(2), 331–344 (2018)
Turk, M.A., Pentland, A.P.: Face recognition using eigenfaces. In: International Conference on Computer Research & Development (2011)
Wang, J., Plataniotis, K.N., Lu, J., Venetsanopoulos, A.N.: On solving the face recognition problem with one training sample per subject. Pattern Recogn. 39(9), 1746–1762 (2006). https://doi.org/10.1016/j.patcog.2006.03.010
Wang, X., Xiong, C., Pei, Q., Qu, Y.: Expression preserved face privacy protection based on multi-mode discriminant analysis. Comput. Mater. Continua 57(1), 107–121 (2018)
Xu, Y., Li, Z., Yang, J., Zhang, D.: A survey of dictionary learning algorithms for face recognition. IEEE Access 5, 8502–8514 (2017). https://doi.org/10.1109/ACCESS.2017.2695239
Yi, H., Xu, Z., Wen, Y., Fan, Z.: Multi-source domain adaptation for face recognition. In: 24th International Conference on Pattern Recognition (ICPR), pp. 1349–1354 (2018). https://doi.org/10.1109/ICPR.2018.8546299
You, K., Long, M., Cao, Z., Wang, J., Jordan, M.I.: Universal domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16–20 June 2019, pp. 2720–2729 (2019)
Acknowledgments
This work is partially supported by The National Natural Science Foundation of China (61662014, 61702130, 61762025), Image intelligent processing project of Key Laboratory Fund (GIIP1804) and Innovation Project of GUET Graduate Education (2018YJCX44).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xu, Z., Han, H., Ji, J., Qiang, B. (2020). Joint Generic Learning and Multi-source Domain Adaptation on Unsupervised Face Recognition. In: Sun, X., Wang, J., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2020. Communications in Computer and Information Science, vol 1252. Springer, Singapore. https://doi.org/10.1007/978-981-15-8083-3_2
Download citation
DOI: https://doi.org/10.1007/978-981-15-8083-3_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-8082-6
Online ISBN: 978-981-15-8083-3
eBook Packages: Computer ScienceComputer Science (R0)