×

Domain adaptation for face recognition: targetize source domain bridged by common subspace. (English) Zbl 1328.68244

Summary: In many applications, a face recognition model learned on a source domain but applied to a novel target domain degenerates even significantly due to the mismatch between the two domains. Aiming at learning a better face recognition model for the target domain, this paper proposes a simple but effective domain adaptation approach that transfers the supervision knowledge from a labeled source domain to the unlabeled target domain. Our basic idea is to convert the source domain images to target domain (termed as targetize the source domain hereinafter), and at the same time keep its supervision information. For this purpose, each source domain image is simply represented as a linear combination of sparse target domain neighbors in the image space, with the combination coefficients however learnt in a common subspace. The principle behind this strategy is that, the common knowledge is only favorable for accurate crossdomain reconstruction, but for the classification in the target domain, the specific knowledge of the target domain is also essential and thus should be mostly preserved (through targetization in the image space in this work). To discover the common knowledge, specifically, a common subspace is learnt, in which the structures of both domains are preserved and meanwhile the disparity of source and target domains is reduced. The proposed method is extensively evaluated under three face recognition scenarios, i.e., domain adaptation across view angle, domain adaptation across ethnicity and domain adaptation across imaging condition. The experimental results illustrate the superiority of our method over those competitive ones.

MSC:

68T45 Machine vision and scene understanding
68T10 Pattern recognition, speech recognition
68T05 Learning and adaptive systems in artificial intelligence
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Belhumeur, P. N., Hespanha, J. P., & Kriegman, D. J. (1997). Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 19(7), 711–720. · Zbl 05111919 · doi:10.1109/34.598228
[2] Ben-David, S., Blitzer, J., Crammer, K., & Pereira, F. (2007). Analysis of representations for domain adaptation. Advances in Neural Information Processing Systems NIPS, 19, 137–144.
[3] Bickel, S., Brückner, M., & Scheffer, T. (2009). Discriminative learning under covariate shift. The Journal of Machine Learning Research (JMLR), 10, 2137–2155. · Zbl 1235.62066
[4] Blitzer, J., McDonald, R., & Pereira, F. (2006). Domain adaptation with structural correspondence learning. In Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 120–128).
[5] Bruzzone, L., & Marconcini, M. (2010). Domain adaptation problems: a dasvm classification technique and a circular validation strategy. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 32(5), 770–787. · doi:10.1109/TPAMI.2009.57
[6] Chen, Y., Wang, G., & Dong, S. (2003). Learning with progressive transductive support vector machine. Pattern Recognition Letters (PRL), 24(12), 1845–1855. · Zbl 01977703 · doi:10.1016/S0167-8655(03)00008-4
[7] Donoho, D. L. (2006). For most large underdetermined systems of linear equations the minimal l \(_{1}\) 1 -norm solution is also the sparsest solution. Communications on Pure and Applied Mathematics, 59(6), 797–829. · Zbl 1113.15004 · doi:10.1002/cpa.20132
[8] Duan, L., Tsang, I. W., Xu, D., & Maybank, S. J. (2009). Domain transfer svm for video concept detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1375–1381).
[9] Duan, L., Xu, D., Tsang, I., & Luo, J. (2012). Visual event recognition in videos by learning from web data. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 34(9), 1667–1680. · doi:10.1109/TPAMI.2011.265
[10] Dudık, M., Schapire, R. E., & Phillips, S. J. (2005). Correcting sample selection bias in maximum entropy density estimation. Advances in Neural Information Processing Systems (NIPS), 17, 323–330.
[11] Efron, B., Hastie, T., Johnstone, I., & Tibshirani, R. (2004). Least angle regression. Annals of Statistics, 39(4), 407–499. · Zbl 1091.62054
[12] Gao, X., Wang, X., Li, X., & Tao, D. (2011). Transfer latent variable model based on divergence analysis. Pattern Recognition (PR), 44(10–11), 2358–2366. · Zbl 1218.68122 · doi:10.1016/j.patcog.2010.06.013
[13] Geng, B., Tao, D., & Xu, C. (2011). Daml: Domain adaptation metric learning. IEEE Transactions on Image Processing (T-IP), 20(10), 2980–2989. · Zbl 1372.68222 · doi:10.1109/TIP.2011.2134107
[14] Gong, B., Shi, Y., Sha, F., & Grauman, K. (2012). Geodesic flow kernel for unsupervised domain adaptation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 0, 2066–2073.
[15] Gopalan, R., Li, R., & Chellappa, R. (2011). Domain adaptation for object recognition: An unsupervised approach. In IEEE International Conference on Computer Vision (ICCV) (pp. 999–1006).
[16] Gretton, A., Smola, A., Huang, J., Schmittfull, M., Borgwardt, K., & Schölkopf, B. (2009). Covariate shift by kernel mean matching. Dataset shift in machine learning (pp. 131–160). Cambridge: MIT Press.
[17] Gross, R., Matthews, I., Cohn, J., kanada, T., & Baker, S. (2007). The cmu multi-pose, illumination, and expression (multi-pie) face database. Tech. rep., Carnegie Mellon University Robotics Institute. TR-07-08.
[18] Hal, DI. (2009). Bayesian multitask learning with latent hierarchies. In Conference on Uncertainty in Artificial Intelligence (UAI) (pp. 135–142).
[19] He, X., & Niyogi, P. (2004). Locality preserving projections. Advances in Neural Information Processing Systems NIPS, 16, 153–160.
[20] Huang, J., Smola, A. J., Gretton, A., Borgwardt, K. M., & Schölkopf, B. (2006). Correcting sample selection bias by unlabeled data. In Advances in Neural Information Processing Systems (NIPS).
[21] Huang, K., & Aviyente, S. (2007). Sparse representation for signal classification. Advances in Neural Information Processing Systems NIPS, 19, 609–616.
[22] Jhuo, IH., Liu, D., Lee, D. T., & Chang, S. F. (2012). Robust visual domain adaptation with low-rank reconstruction. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2168–2175).
[23] Jia, Y., Nie, F., & Zhang, C. (2009). Trace ratio problem revisited. IEEE Transactions on Neural Networks (T-NN), 20(4), 729–735. · doi:10.1109/TNN.2009.2015760
[24] Liu, C., & Wechsler, H. (2002). Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition. IEEE Transactions on Image Processing (T-IP), 11(4), 467–476. · Zbl 05453130 · doi:10.1109/TIP.2002.999679
[25] Mehrotra, R., Agrawal, R., Haider, S. A. (2012). Dictionary based sparse representation for domain adaptation. In ACM International Conference on Information and Knowledge Management (CIKM) (pp. 2395–2398).
[26] Messer, K., Matas, M., Kittler, J., Lttin, J., & Maitre, G. (1999). Xm2vtsdb: The extended m2vts database. In International Conference on Audio and Video-based Biometric Person Authentication (AVBPA) (pp. 72–77).
[27] Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering (T-KDE), 22(10), 1345–1359. · doi:10.1109/TKDE.2009.191
[28] Pan, S. J., Kwok, J. T., & Yang, Q. (2008) Transfer learning via dimensionality reduction. In AAAI Conference on Artificial Intelligence (AAAI) (pp. 677–682).
[29] Pan, S. J., Tsang, I. W., Kwok, J. T., Yang, Q. (2009). Domain adaptation via transfer component analysis. In International Joint Conferences on Artificial Intelligence (IJCAI) (pp. 1187–1192).
[30] Pan, S. J., Tsang, I. W., Kwok, J. T., & Yang, Q. (2011). Domain adaptation via transfer component analysis. IEEE Transactions on Neural Networks (T-NN), 22(2), 199–210. · doi:10.1109/TNN.2010.2091281
[31] Phillips, P. J., Flynn, P. J., Scruggs, T., Bowyer, K. W., Chang, J., Hoffman, K., et al. (2005). Overview of the face recognition grand challenge. IEEE Conference on Computer Vision and Pattern Recognition CVPR, 1, 947–954.
[32] Qiu, Q., Patel, V. M., Turaga, P., & Chellappa, R. (2012). Domain adaptive dictionary learning. In European Conference on Computer Vision (ECCV) (pp. 631–645).
[33] Raina, R., Battle, A., Lee, H., Packer, B., Ng, A. Y. (2007). Self-taught learning: transfer learning from unlabeled data. In International Conference on Machine Learning (ICML) (pp 759–766).
[34] Roweis, S. T., & Saul, L. K. (2000). Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500), 2323–2326.
[35] Shao, M., Castillo, C., Gu, Z., Fu, Y. (2012). Low-rank transfer subspace learning. In IEEE International Conference on Data Mining (ICDM) (pp. 1104–1109).
[36] Shi, Y., & Sha, F. (2012). Information-theoretical learning of discriminative clusters for unsupervised domain adaptation. In International Conference on Machine Learning (ICML).
[37] Shimodaira, Hidetoshi. (2000). Improving predictive inference under covariate shift by weighting the log-likelihood function. Journal of Statistical Planning and Inference, 90(2), 227–244. · Zbl 0958.62011
[38] Si, S., Tao, D., & Geng, B. (2010). Bregman divergence-based regularization for transfer subspace learning. IEEE Transactions on Knowledge and Data Engineering T-KDE, 22(7), 929–942. · doi:10.1109/TKDE.2009.126
[39] Si, S., Liu, W., Tao, D., & Chan, K. P. (2011). Distribution calibration in riemannian symmetric space. IEEE Transactions on Systems, Man, and Cybernetics, Part B, 41(4), 921–930. · doi:10.1109/TSMCB.2010.2100042
[40] Su, Y., Shan, S., Chen, X., & Gao, W. (2009). Hierarchical ensemble of global and local classifiers for face recognition. IEEE Transactions on Image Processing T-IP, 18(8), 1885–1896. · Zbl 1371.94355 · doi:10.1109/TIP.2009.2021737
[41] Sugiyama, M., Nakajima, S., Kashima, H., Buenau, P. V., & Kawanabe, M. (2008). Direct importance estimation with model selection and its application to covariate shift adaptation. In: Advances in Neural Information Processing Systems NIPS, 20, 1433–1440.
[42] Sugiyamai, M., Krauledat, M., & Müller, K. R. (2007). Covariate shift adaptation by importance weighted cross validation. The Journal of Machine Learning Research (JMLR), 8, 985–1005. · Zbl 1222.68313
[43] Turk, M. A., & Pentland, A. P. (1991). Face recognition using eigenfaces. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 591, 586–591.
[44] Uribe, D. (2010). Domain adaptation in sentiment classification. In International Conference on Machine Learning and Applications (ICMLA) (pp. 857–860).
[45] Wang, H., Yan, S., Xu, D., Tang, X., & Huang, T. (2007). Trace ratio vs. ratio trace for dimensionality reduction. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1–8).
[46] Wang, Z., Song, Y., Zhang, C. (2008). Transferred dimensionality reduction. In European Conference on Principles of Data Mining and Knowledge Discovery (PKDD) (pp. 550–565).
[47] Wright, J., Yang, A. Y., Ganesh, A., Sastry, S. S., & Ma, Y. (2009). Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 31(2), 210–227. · doi:10.1109/TPAMI.2008.79
[48] XianJiaotong, U. (2006). http://www.aiar.xjtu.edu.cn/dfrlsjk5.htm .
[49] Xue, Y., Liao, X., Carin, L., & Krishnapuram, B. (2007). Multi-task learning for classification with dirichlet process priors. The Journal of Machine Learning Research (JMLR), 8, 35–63. · Zbl 1222.68338
[50] Zadrozny, & Bianca (2004). Learning and evaluating classifiers under sample selection bias. In Proceedings of International Conference on Machine Learning (ICML) (p. 114).
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.