Abstract
The standard machine learning tasks often assume that the training (source domain) and test (target domain) data follow the same distribution and feature space. However, many real-world applications suffer from the limited number of training labeled data and benefit from the related available labeled datasets to train the model. In this way, since there is the distribution difference across the source and target domains (i.e., domain shift problem), the learned classifier on the training set might perform poorly on the test set. To address the shift problem, domain adaptation provides variety of solutions to learn robust classifiers to deal with distribution mismatch across the source and target domains. In this paper, we put forward a novel domain adaptation approach, referred to as cross- and multiple-domains visual transfer learning via iterative Fischer linear discriminant analysis (CIDA) to tackle shift problem across domains. CIDA transfers the source and target domains into a shared low-dimensional Fischer linear discriminant analysis (FLDA)-based subspace in an unsupervised manner. CIDA benefits joint FLDA and domain adaptation criterions to reduce the distribution mismatch across the training and test sets. Moreover, CIDA employs an adaptive classifier to build a robust model against data drift across different domains. Also, CIDA generates the intermediate pseudotarget labels to utilize the target data in training process. In this way, CIDA refines the pseudolabels using an iterative manner to converge the model. Our extensive experiments illustrate that CIDA significantly outperforms the baseline machine learning and other state-of-the-art transfer learning methods on nine visual benchmark datasets under different difficulties.
Similar content being viewed by others
References
Mahya A, Jafar T (2021) Metric transfer learning via geometric knowledge embedding. Appl Intell 51(2):921–934
Karimpour M, Saray SN, Tahmoresnezhad J, Pourmahmood AM (2020) Multi-source domain adaptation for image classification. Mach Vis Appl 31(6):1–19
John B, Mark D, Fernando P et al (2007) Biographies, bollywood, boom-boxes and blenders: domain adaptation for sentiment classification. ACL 7:440–447
Sanodiya RK, Paul D, Yao L, Mathew J, Juhi A (2020) A feature selection approach to visual domain adaptation in classification. In: International conference on neural information processing, Springer, pp 77–89
Wang F, Ding Y, Liang H, Wen J (2021) Discriminative and selective pseudo-labeling for domain adaptation. In: International conference on multimedia modeling, Springer, pp 365–377
Blitzer J, McDonald R, Pereira F (2006) 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
Chen M, Weinberger KQ, Blitzer J (2011) Co-training for domain adaptation. In: Advances in neural information processing systems, pp 2456–2464
Gong B, Shi Y, Sha F, Grauman K (2012) Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE conference on Computer vision and pattern recognition (CVPR), IEEE, pp 2066–2073
Gopalan R, Li R, Chellappa R (2011) Domain adaptation for object recognition: an unsupervised approach. In: 2011 IEEE international conference on computer vision (ICCV), IEEE, pp 999–1006
Tahmoresnezhad J, Hashemi S (2016) Transductive transfer learning via maximum margin criterion. Sci Iran 23(3):1239–1250
Bergamo A, Torresani L (2010) Exploiting weakly-labeled web images to improve object classification: a domain adaptation approach. In: Advances in neural information processing systems, pp 181–189
Kumar A, Saha A, Daume H (2010) Co-regularization based semi-supervised domain adaptation. In: Advances in neural information processing systems, pp 478–486
Kate S, Brian K, Mario F, Trevor D (2010) Adapting visual category models to new domains. Comput Vis ECCV 2010:213–226
Ben-David S, Blitzer J, Crammer K, Pereira F (2007) Analysis of representations for domain adaptation. In: Advances in neural information processing systems, pp 137–144
Ciprian C, Alex A (2006) Adaptation of maximum entropy capitalizer: little data can help a lot. Comput Speech Lang 20(4):382–399
Hal Daume III and Daniel Marcu (2006) Domain adaptation for statistical classifiers. J Artif Intell Res 26:101–126
Jafar T, Sattar H (2017) Exploiting kernel-based feature weighting and instance clustering to transfer knowledge across domains. Turk J Electr Eng Comput Sci 25(1):292–307
Mansour Y, Mohri M, Rostamizadeh A (2009) Domain adaptation with multiple sources. In: Advances in neural information processing systems, pp 1041–1048
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):151–175
Crammer K, Earns M, Wortman J (2008) Learning from multiple sources. J Mach Learn Res, 9(Aug):1757–1774
Tahmoresnezhad J, Hashemi S (2015) Common feature extraction in multi-source domains for transfer learning. In: 2015 7th conference on information and knowledge technology (IKT), IEEE, pp 1–5
Fan W, Davidson I, Zadrozny B, Yu PS (2005) An improved categorization of classifier’s sensitivity on sample selection bias. In: Fifth IEEE international conference on data mining, IEEE
Gong B, Grauman K, Sha F (2013) Connecting the dots with landmarks: discriminatively learning domain-invariant features for unsupervised domain adaptation. In: International conference on machine learning, pp 222–230
Jing J, ChengXiang Z (2007) Instance weighting for domain adaptation in nlp. ACL 7:264–271
Sugiyama M, Nakajima S, Kashima H, Buenau PV, Kawanabe M (2008) Direct importance estimation with model selection and its application to covariate shift adaptation. In: Advances in neural information processing systems, pp 1433–1440
Samaneh R, Jafar T, Vahid S (2021) A transductive transfer learning approach for image classification. Int J Mach Learn Cybernet 12(3):747–762
Long M, Wang J, Ding G, Sun J, Yu PS (2014) Transfer joint matching for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1410–1417
Satpal S, Sarawagi S (2007) Domain adaptation of conditional probability models via feature subsetting. In: PKDD, vol 4702, pp 224–235. Springer
Pan SJ, Tsang IW, Kwok JT, Yang Q (2011) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22(2):199–210
Si S, Dacheng T, Bo G (2010) Bregman divergence-based regularization for transfer subspace learning. IEEE Trans Knowl Data Eng 22(7):929–942
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
Duan L, Tsang IW, Xu D, Maybank SJ (2009) Domain transfer svm for video concept detection. In: CVPR 2009. IEEE conference on computer vision and pattern recognition
Lorenzo B, Mattia M (2010) Domain adaptation problems: a dasvm classification technique and a circular validation strategy. IEEE Trans Pattern Anal Mach Intell 32(5):770–787
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):1076–1089
Shiva Noori Saray and Jafar Tahmoresnezhad (2021) Joint distinct subspace learning and unsupervised transfer classification for visual domain adaptation. SIViP 15(2):279–287
Marzieh Gheisari and Mahdieh Soleymani Baghshah (2015) Unsupervised domain adaptation via representation learning and adaptive classifier learning. Neurocomputing 165:300–311
Elahe G, Jafar T (2020) Joint discriminative subspace and distribution adaptation for unsupervised domain adaptation. Appl Intell 50(7):2050–2066
Vural Elif (2018) Generalization bounds for domain adaptation via domain transformations. In: 2018 IEEE 28th international workshop on machine learning for signal processing (MLSP), IEEE, pp 1–6
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 1:1–1
Kouw WM, Van Der Maaten LJP, Krijthe JH, Loog M (2016) Feature-level domain adaptation. J Mach Learn Res 17(1):5943–5974
Long M, Wang J, Ding G, Sun J, Yu PS (2013) Transfer feature learning with joint distribution adaptation. In: Proceedings of the IEEE international conference on computer vision, pp 2200–2207
Jafar T, Sattar H (2017) Visual domain adaptation via transfer feature learning. Knowl Inf Syst 50(2):585–605
Dinh CV, Duin RPW, Piqueras-Salazar I, Loog M (2013) Fidos: a generalized fisher based feature extraction method for domain shift. Pattern Recogn 46(9):2510–2518
Wenting Tu, Shiliang Sun (2012) Cross-domain representation-learning framework with combination of class-separate and domain-merge objectives. In Proceedings of the 1st International Workshop on Cross Domain Knowledge Discovery in Web and Social Network Mining, pages 18–25. ACM
Wang Z, Song Y, Zhang C (2008) Transferred dimensionality reduction. Mach Learn Knowl Discov Databases, pp 550–565
Borgwardt KM, Gretton A, Rasch MJ, Kriegel H-P, Schölkopf B, Smola AJ (2006) Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics 22(14):e49–e57
Yao Y, Doretto G (2010) Boosting for transfer learning with multiple sources. In: 2010 IEEE conference on computer vision and pattern recognition (CVPR), pp 1855–1862. IEEE
Yoshida Y, Hirao T, Iwata T, Nagata M, Matsumoto Y (2011) Transfer learning for multiple-domain sentiment analysis-identifying domain dependent/independent word polarity. In: AAAI
Moreno O, Shapira B, Rokach L, Shani G (2012) Talmud: transfer learning for multiple domains. In: Proceedings of the 21st ACM international conference on Information and knowledge management, ACM, pp 425–434
Li S, Zong C (2008) Multi-domain adaptation for sentiment classification: Using multiple classifier combining methods. In: International conference on natural language processing and knowledge engineering, 2008. NLP-KE’08, IEEE, pp 1–8
Rita C, Qian S, Wei F, Ian D, Sethuraman P, Jieping Y (2012) Multisource domain adaptation and its application to early detection of fatigue. ACM Trans Knowl Discov Data (TKDD) 6(4):18
Zhang Y, Cao B, Yeung D-Y (2010) Multi-domain collaborative filtering. In: Proceedings of the twenty-sixth conference on uncertainty in artificial intelligence, UAI’10, Arlington, Virginia, United States, AUAI Press, pp 725–732
Belkin M, Niyogi P, Sindhwani V (2006) Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res, 7(Nov):2399–2434
Ulrike VL (2007) A tutorial on spectral clustering. Stat Comput 17(4):395–416
Schölkopf B, Herbrich R, Smola A (2001) A generalized representer theorem. In: Computational learning theory, Springer, pp 416–426
Long M, Wang J, Sun J, Yu Philip S (2015) Domain invariant transfer kernel learning. IEEE Trans Knowl Data Eng 27(6):1519–1532
Griffin G, Holub A, Perona P 2007) Caltech-256 object category dataset
Herbert B, Tinne T, Luc VG (2006) Surf: speeded up robust features. Comput Vis ECCV 2006:404–417
Ming S, Dmitry K, Yun F (2014) Generalized transfer subspace learning through low-rank constraint. Int J Comput Vision 109(1–2):74–93
Yong X, Xiaozhao F, Jian W, Xuelong L, David Z (2016) Discriminative transfer subspace learning via low-rank and sparse representation. IEEE Trans Image Process 25(2):850–863
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
Mardani, M., Tahmoresnezhad, J. Cross- and multiple-domains visual transfer learning via iterative Fischer linear discriminant analysis. Knowl Inf Syst 63, 2157–2188 (2021). https://doi.org/10.1007/s10115-021-01586-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-021-01586-0