Abstract
In traditional machine learning algorithms, the classification models are learned on the training data (source domain) to reuse for labelling the test data (target domain) where the training and test samples are from the same distributions. However in nowadays applications, the existence of distribution shift across the source and target doamins degrades the model performance, significantly. Domain adaptation methods have been proposed to compensate domain shift problem by aligning the distributions across the source and target domains under various adaptation strategies. This paper addresses the robust image classification problem for unsupervised domain adaptation. Specifically, following three methods are proposed: Discriminative Subspace Learning (DSL), Joint Geometrical and Statistical Distribution Adaptation (GSDA), and Joint Subspace and Distribution Adaptation (DSL-GSDA). DSL is a subspace centric method that aligns the specific and shared features across domains. Indeed, DSL finds two projections to map the source and target data into independent subspaces by aligning the discriminant and global structures of domains. GSDA trends to find an adaptive classifier through statistical and geometrical distribution alignment and minimizes the prediction error. DSL-GSDA, as a combination of DSL and GSDA, consists of two subspace and distribution adaptation levels. DSL-GSDA uses DSL to build two aligned subspaces of source and target domains. The distributions of source and target data in new subspaces is adapted via GSDA. The proposed methods are evaluated on benchmark visual datasets for object, digit and face recongnition tasks. Visual datasets consist of image domains that have been captured under various real-world conditions where the domain shift is unavoidable. The experiment results show that DSL, GSDA and DSL-GSDA outperform other state-of-the-art domain adaptation methods by 6.19%, 1.48% and 1.99% improvement, respectively. Our source code is available at https://github.com/jtahmores/DSLGSDA (https://github.com/jtahmores/DSLGSDA).
Similar content being viewed by others
References
Shi Y, Sha F (2012) Information-theoretical learning of discriminative clusters for unsupervised domain adaptation. arXiv:1206.6438
Gong B, Grauman K, Sha F (2013) Reshaping visual datasets for domain adaptation. In: Advances in Neural Information Processing Systems, pp 1286–1294
Jhuo IH, Liu D, Lee DT, Chang SF (2012) Robust visual domain adaptation with low-rank reconstruction. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 2168–2175
Daume H III, Marcu D (2006) Domain adaptation for statistical classifiers. J Artif Intell Res 26:101–126
Patel VM, Gopalan R, Li R, Chellappa R (2015) Visual domain adaptation: a survey of recent advances. IEEE Signal Process Mag 32(3):53–69
Hana D, Liu Q, Fan W (2017) A New Image Classification Method Using CNN transfer learning and Web Data Augmentation. Expert Systems with Applications
Luo Z, Hu J, Deng W, Shen H (2018) Deep unsupervised domain adaptation for face recognition. In: 2018 13th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2018). IEEE, pp 453–457
Wen G, Chen H, Cai D, He X (2018) Improving face recognition with domain adaptation. Neurocomputing 287:45–51
Blitzer J, Dredze M, Pereira F (2007) Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. In: ACL, vol 7, pp 440–447
Glorot X, Bordes A, Bengio Y (2011) Domain adaptation for large-scale sentiment classification: a deep learning approach. In: Proceedings of the 28th international conference on machine learning (ICML-11), pp 513–520
Sun Y, Tzeng E, Darrell T, Efros AA (2019) Unsupervised Domain Adaptation through Self-Supervision. arXiv:1909.11825
Ciga O, Chen J, Martel A (2019) Multi-layer Domain Adaptation for Deep Convolutional Networks. In: Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data. Springer, Cham, pp 20–27
Yang J, Yan R, Hauptmann AG (2007) Cross-domain video concept detection using adaptive svms. In: Proceedings of the 15th ACM international conference on Multimedia. ACM, pp 188–197
Duan L, Xu D, Tsang IWH, Luo J (2012) Visual event recognition in videos by learning from web data. IEEE Trans Pattern Anal Mach Intell 34(9):1667–1680
Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. In: European conference on computer vision. Springer, Berlin, pp 213–226
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: International conference on machine learning, pp 647–655
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc. IEEE 86(11):2278–2324
Griffin G, Holub A, Perona P (2007) Caltech-256 object category dataset
Sim T, Baker S, Bsat M (2001) The CMU pose, illumination and expression (PIE) database of human faces. Carnegie Mellon University, The Robotics Institute
Blitzer J, McDonald R, Pereira F (2006) July) Domain adaptation with structural correspondence learning. In: Proceedings of the 2006 conference on empirical methods in natural language processing. Association for Computational Linguistics, pp 120–128
Jiang J, Zhai C (2007) Instance weighting for domain adaptation in NLP. In: Proceedings of the 45th annual meeting of the association of computational linguistics, pp 264–271
Bruzzone L, Marconcini M (2010) Domain adaptation problems: a DASVM classification technique and a circular validation strategy. IEEE Trans Pattern Anal Mach Intell 32(5):770–87
Sun Q, Chattopadhyay R, Panchanathan S, Ye J (2011) A two-stage weighting framework for multi-source domain adaptation. In: Advances in neural information processing systems, pp 505–513
Long M, Wang J, Ding G, Pan SJ, Philip SY (2014) Adaptation regularization: a general framework for transfer learning. IEEE Trans Knowl Data Eng 26(5):1076–89
Luo L, Chen L, Hu S, Lu Y, Wang X (2017) Discriminative and geometry aware unsupervised domain adaptation. arXiv:1712.10042
Pan SJ, Tsang IW, Kwok JT, Yang Q (2011) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22(2):199–210
Long M, Wang J, Ding G, Sun J, Philip SY (2013, December) Transfer feature learning with joint distribution adaptation. In: 2013 IEEE International Conference on Computer Vision (ICCV). IEEE, pp 2200–2207
Tahmoresnezhad J, Hashemi S (2017) Visual domain adaptation via transfer feature learning. Knowl Inf Syst 50(2):585–605
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):850–63
Luo L, Wang X, Hu S, Chen L (2017) Robust data geometric structure aligned close yet discriminative domain adaptation. arXiv:1705.08620
Wang J, Chen Y, Hao S, Feng W, Shen Z (2017) Balanced distribution adaptation for transfer learning. In: 2017 IEEE International Conference on Data Mining (ICDM). IEEE, pp 1129–1134
Ghifary M, Balduzzi D, Kleijn WB, Zhang M (2017) Scatter component analysis: a unified framework for domain adaptation and domain generalization. IEEE Trans Pattern Anal Mach Intell 39(7):1414–30
Liu J, Li J, Lu K (2018) Coupled local–global adaptation for multi-source transfer learning. Neurocomputing 275:247–54
Liang J, He R, Sun Z, Tan T (2018) Aggregating randomized clustering-promoting invariant projections for domain adaptation. IEEE Trans Pattern Anal Mach Intell 41(5):1027–1042
Fernando B, Habrard A, Sebban M (2013) Tuytelaars T (2013, December) Unsupervised visual domain adaptation using subspace alignment. In: Computer Vision (ICCV) IEEE International Conference. IEEE, pp 2960–2967
Sun B, Saenko K (2015) Subspace distribution alignment for unsupervised domain adaptation. In: BMVC, pp 24–1
Zhang J, Li W, Ogunbona P (2017) Joint geometrical and statistical alignment for visual domain adaptation. arXiv:1705.05498
Gholenji E, Tahmoresnezhad J (2019) Joint local and statistical discriminant Llearning via feature alignment. Signal, Image and Video Processing. https://doi.org/10.1007/s11760-019-01587-1
Rezaei S, Tahmoresnezhad J (2019) Discriminative and domain invariant subspace alignment for visual tasks. Iran Journal of Computer Science 2:219–230. https://doi.org/10.1007/s42044-019-00037-y
Mardani M, Tahmoresnezhad J (2018) Joint Distribution Adaptation via Feature and Model Matching. Scientia Iranica
Tahmoresnezhad J, Hashemi S (2015) A generalized kernel-based random k-samplesets method for transfer learning. Iran J Sci Technol Trans Electr Eng 39:193–207
Abdi H, Williams LJ (2010) Principal component analysis. Wiley Interdiscip Rev Comput Stat 2(4):433–59
Wang J, Feng W, Chen Y, Yu H, Huang M, Yu PS (2018) Visual domain adaptation with manifold embedded distribution alignment. In: 2018 ACM Multimedia Conference on Multimedia Conference. ACM, pp 402–410
Gopalan R, Li R, Chellappa R (2011) Domain adaptation for object recognition: An unsupervised approach. In: 2011 international conference on computer vision. IEEE, pp 999–1006
Welling M (2005) Fisher linear discriminant analysis. Department of Computer Science, University of Toronto 3(1)
McLachlan GJ (2004) Discriminant analysis and statistical pattern recognition, John Wiley and Sons, 544
Harel M, Mannor S (2010) Learning from multiple outlooks. arXiv:1005.0027
Alvarez MA, Rosasco L, Lawrence ND (2012) Kernels for vector-valued functions: a review. Found Trends Mach Learn 4(3):195–266
Schölkopf B, Herbrich R, Smola AJ (2001) A generalized representer theorem. In: International conference on computational learning theory, pp 416–426
Gretton A, Borgwardt K, Rasch MJ, Scholkopf B, Smola AJ (2008) A kernel method for the two-sample problem. arXiv:0805.2368
Belkin M, Niyogi P, Sindhwani V (2006) Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learni Res 7(Nov):2399–434
Li J, Lu K, Huang Z, Zhu L, Shen HT (2018) Transfer independently together: a generalized framework for domain adaptation. IEEE Trans Cybern 49(6):2144–2155
Li S, Song S, Huang G, Ding Z, Wu C (2018) Domain invariant and class discriminative feature learning for visual domain adaptation. IEEE Trans Image Process 27(9):4260–4273
Uzair M, Mian A (2016) Blind domain adaptation with augmented extreme learning machine features. IEEE Trans Cybern 47(3):651–660
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Long M, Cao Y, Wang J, Jordan MI (2015) Learning transferable features with deep adaptation networks. arXiv:1502.02791
Tzeng E, Hoffman J, Zhang N, Saenko K, Darrell T (2014) Deep domain confusion: Maximizing for domain invariance. arXiv:1412.3474
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: Proceedings of the IEEE International Conference on Computer Vision, pp 599–608
Gholami B, Pavlovic V (2017) Punda: Probabilistic unsupervised domain adaptation for knowledge transfer across visual categories. In: Proceedings of the IEEE International Conference on Computer Vision, pp 3581–3590
Author information
Authors and Affiliations
Corresponding author
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
Gholenji, E., Tahmoresnezhad, J. Joint discriminative subspace and distribution adaptation for unsupervised domain adaptation. Appl Intell 50, 2050–2066 (2020). https://doi.org/10.1007/s10489-019-01610-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-019-01610-5