Abstract
This work focuses on unsupervised visual domain adaptation which is still challenging in visual recognition. Most of the attention has been dedicated to seeking the domain-invariant features of cross-domain data, but they ignores the valuable discriminative information in the source domain. In this paper, we propose a Discriminative Dictionary Evolution (DDE) approach to seek discriminative features robust to domain shift. Specifically, DDE gradually adapts a discriminative dictionary learned from the source domain to the target domain through a dictionary evolving procedure, in which self-selected atoms of the dictionary are updated with \(\ell _{2,1}\)-norm-based regularization. DDE produces domain-invariant representations for cross-domain visual recognition meanwhile promotes the discriminativeness of the dictionary. Empirical results on real-world data sets demonstrate the advantages of the proposed approach over existing competitive methods.
Similar content being viewed by others
References
Baktashmotlagh M, Harandi MT, Lovell BC, Salzmann M (2013) Unsupervised domain adaptation by domain invariant projection. In: ICCV, pp 769–776
Baktashmotlagh M, Harandi MT, Lovell BC, Salzmann M (2014) Domain adaptation on the statistical manifold. In: CVPR, pp 2481–2488
Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan JW (2010) A theory of learning from different domains. Mach Learn 79(1–2):151–175
Chen M, Weinberger K, Sha F, Bengio Y (2014) Marginalized denoising auto-encoders for nonlinear representations. In: ICML, pp 1476–1484
Donahue J, Jia Y, Vinyals O, Hoffman J, Zhang N, Tzeng E, Darrell T (2014) Decaf: a deep convolutional activation feature for generic visual recognition. In: ICML, pp 647–655
Duan L, Tsang IW, Xu D (2012) Domain transfer multiple kernel learning. IEEE Trans Pattern Anal Mach Intell 34(3):465–479
Duan L, Tsang IW, Xu D, Chua T (2009) Domain adaptation from multiple sources via auxiliary classifiers. In: ICML, pp 289–296
Fernando B, Habrard A, Sebban M, Tuytelaars T (2013) Unsupervised visual domain adaptation using subspace alignment. In: ICCV, pp 2960–2967
Ganin Y, Lempitsky V (2015) Unsupervised domain adaptation by backpropagation. In: Proceedings of the 32nd international conference on machine learning, vol 37, pp 1180–1189
Ghifary M, Kleijn WB, Zhang M, Balduzzi D, Li W (2016) Deep reconstruction-classification networks for unsupervised domain adaptation. In: ECCV, pp 597–613
Gong B, Grauman K, Sha F (2014) Learning kernels for unsupervised domain adaptation with applications to visual object recognition. Int J Comput Vis 109(1–2):3–27
Gong B, Shi Y, Sha F, Grauman K (2012) Geodesic flow kernel for unsupervised domain adaptation. In: CVPR, pp 2066–2073
Gopalan R, Li R, Chellappa R (2011) Domain adaptation for object recognition: an unsupervised approach. In: ICCV, pp 999–1006
Gopalan R, Li R, Chellappa R (2014) Unsupervised adaptation across domain shifts by generating intermediate data representations. IEEE Trans Pattern Anal Mach Intell 36(11):2288–2302
Gretton A, Borgwardt KM, Rasch MJ, Schölkopf B, Smola A (2012) A kernel two-sample test. J Mach Learn Res 13:723–773
Griffin G, Holub A, Perona P (2007) Caltech-256 Object Category Dataset. Tech. Rep, California Institute of Technology
Gross R, Matthews I, Cohn JF, Kanade T, Baker S (2010) Multi-pie. Image Vis Comput 28(5):807–813
Huang D, Wang YF (2013) Coupled dictionary and feature space learning with applications to cross-domain image synthesis and recognition. In: ICCV, pp 2496–2503
Hull JJ (1994) A database for handwritten text recognition research. IEEE Trans Pattern Anal Mach Intell 16(5):550–554
Jiang Z, Lin Z, Davis LS (2013) Label consistent K-SVD: learning a discriminative dictionary for recognition. IEEE Trans Pattern Anal Mach Intell 35(11):2651–2664
Kan M, Wu J, Shan S, Chen X (2014) Domain adaptation for face recognition: targetize source domain bridged by common subspace. Int J Comput Vis 109(1–2):94–109
Kulis B, Saenko K, Darrell T (2011) What you saw is not what you get: domain adaptation using asymmetric kernel transforms. In: CVPR, pp 1785–1792
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, pp 2278–2324
Li W, Duan L, Xu D, Tsang IW (2014) Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation. IEEE Trans Pattern Anal Mach Intell 36(6):1134–1148
Long M, Ding G, Wang J, Sun J, Guo Y, Yu PS (2013) Transfer sparse coding for robust image representation. In: CVPR, pp 407–414
Long M, Wang J, Cao Y, Sun J, Yu PS (2016) Deep learning of transferable representation for scalable domain adaptation. IEEE Trans Knowl Data Eng 28(8):2027–2040
Long M, Wang J, Ding G, Sun J, Yu PS (2014) Transfer joint matching for unsupervised domain adaptation. In: CVPR, pp 1410–1417
Long M, Wang J, Sun J, Yu PS (2015) Domain invariant transfer kernel learning. IEEE Trans Knowl Data Eng 27(6):1519–1532
Long M, Zhu H, Wang J, Jordan MI (2016) Unsupervised domain adaptation with residual transfer networks. In: Advances in neural information processing systems, pp 136–144
Lu H, Zhang L, Cao Z, Wei W, Xian K, Shen C, van den Hengel A (2017) When unsupervised domain adaptation meets tensor representations. In: ICCV, pp 599–608
Motiian S, Piccirilli M, Adjeroh DA, Doretto G (2017) Unified deep supervised domain adaptation and generalization. In: ICCV, pp 5715–5725
Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng AY (2011) Reading digits in natural images with unsupervised feature learning. In: NIPS
Ni J, Qiu Q, Chellappa R (2013) Subspace interpolation via dictionary learning for unsupervised domain adaptation. In: CVPR, pp 692–699
Pan SJ, Kwok JT, Yang Q (2008) Transfer learning via dimensionality reduction. In: AAAI, pp 677–682
Pan SJ, Tsang IW, Kwok JT, Yang Q (2011) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22(2):199–210
Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359
Patel V, Gopalan R, Li R, Chellappa R (2015) Visual domain adaptation: a survey of recent advances. IEEE Signal Process Magazine 32(3):53–69
Qiu Q, Patel VM, Turaga PK, Chellappa R (2012) Domain adaptive dictionary learning. In: ECCV, pp 631–645
Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. In: ECCV, pp 213–226
Shekhar S, Patel VM, Nguyen HV, Chellappa R (2015) Coupled projections for adaptation of dictionaries. IEEE Trans Image Process 24(10):2941–2954
Shi Y, Sha F (2012) Information-theoretical learning of discriminative clusters for unsupervised domain adaptation. In: ICML, pp 1275–1282
Shu L, Ma T, Latecki LJ (2014) Locality preserving projection for domain adaptation with multi-objective learning. In: AAAI, pp 2085–2091
Sun H, Liu S, Zhou S (2016) Discriminative subspace alignment for unsupervised visual domain adaptation. Neural Process Lett 44(3):779–793
Tzeng E, Hoffman J, Saenko K, Darrell T (2017) Adversarial discriminative domain adaptation. In: CVPR, pp 7167–7176
Tzeng E, Hoffman J, Zhang N, Saenko K, Darrell T (2014) Deep domain confusion: maximizing for domain invariance. ArXiv preprint arXiv:1412.3474 (2014)
Volpi R, Morerio P, Savarese S, Murino V (2018) Adversarial feature augmentation for unsupervised domain adaptation. In: CVPR, pp 5495–5504
Wang J, Li X, Du J (2018) Label space embedding of manifold alignment for domain adaption. Neural Process Lett. https://doi.org/10.1007/s11063-018-9822-8
Wu S, Jing XY, Yue D, Zhang J, Yang J, Yang J (2016) Unsupervised visual domain adaptation via dictionary evolution. In: 2016 IEEE international conference on multimedia and expo (ICME), pp 1–6
Xiao M, Guo Y (2012) Semi-supervised kernel matching for domain adaptation. In: AAAI, pp 1183–1189
Xie X, Sun S, Chen H, Qian J (2017) Domain adaptation with twin support vector machines. Neural Process Lett. https://doi.org/10.1007/s11063-017-9775-3
Xu X, Shimada A, Taniguchi R, He L (2015) Coupled dictionary learning and feature mapping for cross-modal retrieval. In: ICME, pp 1–6
Xu Y, Fang X, Wu J, Li X, Zhang D (2016) Discriminative transfer subspace learning via low-rank and sparse representation. IEEE Trans Image Process 25(2):850–863
Yang M, Zhang L, Feng X, Zhang D (2011) Fisher discrimination dictionary learning for sparse representation. In: ICCV, pp 543–550
Zadrozny B (2004) Learning and evaluating classifiers under sample selection bias. In: ICML, pp 114–122
Zelnik-Manor L, Perona P (2004) Self-tuning spectral clustering. In: NIPS, pp 1601–1608
Zhang XY, Liu CL (2013) Writer adaptation with style transfer mapping. IEEE Trans Pattern Anal Mach Intell 35(7):1773–1787
Zheng J, Jiang Z, Phillips PJ, Chellappa R (2012) Cross-view action recognition via a transferable dictionary pair. In: BMVC, pp 1–11
Funding
This work is supported by the National Natural Science Foundation of China under Grant Nos. 61402238, 61502245, 61972212; the Natural Science Foundation of Jiangsu Province under Grant No. BK20190089; Industrial Robot Application of Fujian University Engineering Research Center, Minjiang University under Grant No. MJUKF-IRA201806.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wu, S., Gao, G., Li, Z. et al. Unsupervised visual domain adaptation via discriminative dictionary evolution. Pattern Anal Applic 23, 1665–1675 (2020). https://doi.org/10.1007/s10044-020-00881-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-020-00881-w