Volume 17, Issue 2 (9-2020)
JSDP 2020, 17(2): 58-47 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Sherafati F, Tahmoresnezhad J. Image Classification via Sparse Representation and Subspace Alignment. JSDP 2020; 17 (2) :58-47
URL: http://jsdp.rcisp.ac.ir/article-1-887-en.html
URL: http://jsdp.rcisp.ac.ir/article-1-887-en.html
Urmia University of Technology
Abstract: (2512 Views)
Image representation is a crucial problem in image processing where there exist many low-level representations of image, i.e., SIFT, HOG and so on. But there is a missing link across low-level and high-level semantic representations. In fact, traditional machine learning approaches, e.g., non-negative matrix factorization, sparse representation and principle component analysis are employed to describe the hidden semantic information in images, where they assume that the training and test sets are from same distribution. However, due to the considerable difference across the source and target domains result in environmental or device parameters, the traditional machine learning algorithms may fail.
Transfer learning is a promising solution to deal with above problem, where the source and target data obey from different distributions. For enhancing the performance of model, transfer learning sends the knowledge from the source to target domain. Transfer learning benefits from sample reweighting of source data or feature projection of domains to reduce the divergence across domains.
Sparse coding joint with transfer learning has received more attention in many research fields, such as signal processing and machine learning where it makes the representation more concise and easier to manipulate. Moreover, sparse coding facilitates an efficient content-based image indexing and retrieval.
In this paper, we propose image classification via Sparse Representation and Subspace Alignment (SRSA) to deal with distribution mismatch across domains in low-level image representation. Our approach is a novel image optimization algorithm based on the combination of instance-based and feature-based techniques. Under this framework, we reweight the source samples that are relevant to target samples using sparse representation. Then, we map the source and target data into their respective and independent subspaces. Moreover, we align the mapped subspaces to reduce the distribution mismatch across domains. The proposed approach is evaluated on various visual benchmark datasets with 14 experiments. Comprehensive experiments demonstrate that SRSA outperforms other latest machine learning and domain adaptation methods with significant difference.
Transfer learning is a promising solution to deal with above problem, where the source and target data obey from different distributions. For enhancing the performance of model, transfer learning sends the knowledge from the source to target domain. Transfer learning benefits from sample reweighting of source data or feature projection of domains to reduce the divergence across domains.
Sparse coding joint with transfer learning has received more attention in many research fields, such as signal processing and machine learning where it makes the representation more concise and easier to manipulate. Moreover, sparse coding facilitates an efficient content-based image indexing and retrieval.
In this paper, we propose image classification via Sparse Representation and Subspace Alignment (SRSA) to deal with distribution mismatch across domains in low-level image representation. Our approach is a novel image optimization algorithm based on the combination of instance-based and feature-based techniques. Under this framework, we reweight the source samples that are relevant to target samples using sparse representation. Then, we map the source and target data into their respective and independent subspaces. Moreover, we align the mapped subspaces to reduce the distribution mismatch across domains. The proposed approach is evaluated on various visual benchmark datasets with 14 experiments. Comprehensive experiments demonstrate that SRSA outperforms other latest machine learning and domain adaptation methods with significant difference.
Keywords: Image classification, Visual domains adaptation, Sparse representation, Subspace alignment
Type of Study: Research |
Subject:
Paper
Received: 2018/08/18 | Accepted: 2019/11/3 | Published: 2020/09/14 | ePublished: 2020/09/14
Received: 2018/08/18 | Accepted: 2019/11/3 | Published: 2020/09/14 | ePublished: 2020/09/14
References
1. [1] Y. Zhang, T. Liu, M. Long, and M. I. Jordan, "Bridging Theory and Algorithm for Domain Adaptation", arXiv preprint arXiv:1904.05801, 2019.
2. [2] S. Rezaei and J. Tahmoresnezhad, "Discriminative and domain invariant subspace alignment for visual tasks", Iran Journal of Computer Science, pp. 1-12, 2019. [DOI:10.1007/s42044-019-00037-y]
3. [3] W. Kumagai and T. Kanamori, "Risk bound of transfer learning using parametric feature mapping and its application to sparse coding", Machine Learning, pp. 1-34, 2019. [DOI:10.1007/s10994-019-05805-2]
4. [4] I. Jolliffe "Principal component analysis", Wiley, vol. 2, pp. 433-459, 2002. [DOI:10.1002/wics.101]
5. [5] M. Jing, J. Li, J. Zhao, and K. Lu, "Learning distribution-matched landmarks for unsupervised domain adaptation", In International conference on database systems for advanced applications, pp. 491-508, 2018. [DOI:10.1007/978-3-319-91458-9_30]
6. [6] A. Li, D. Chen, Z. Wu, G. Sun, and K. Lin, "Self-supervised sparse coding scheme for image classification based on low rank represent-tation", PloS one, Vol. 13(6), e0199141, 2018. [DOI:10.1371/journal.pone.0199141] [PMID] [PMCID]
7. [7] A. Mirjalili, V. Abootalebi, M. T. Sadeghi, "mproving the performance of sparse representation-based classifier for EEG classification," JSDP , pp. 43-55, 2015.
8. [8] X. Li, M. Fang, J. J. Zhang and J. Wu, "Sample selection for visual domain adaptation via sparse coding", Signal Processing: Image Communi-cation, vol. 44, pp. 92-100, 2016. [DOI:10.1016/j.image.2016.03.009]
9. [9] B. Gong, Y. Shi, F. Sha and K. Grauman, "Geodesic flow kernel for unsupervised domain adaptation", Proceedings of the IEEE Con-ference on Computer Vision and Pattern Recog-nition, pp. 2066-2073, 2012.
10. [10] S. J. Pan, I. W. Tsang, J. T. Kwok and Q. Yang, "Domain adaptation via transfer component analysis", IEEE Trans. Neural Netw, vol. 22, no. 2, pp. 199-210, 2011. [DOI:10.1109/TNN.2010.2091281] [PMID]
11. [11] B. Fernando, A. Habrard, M. Sebban, and T. Tuytelaars, "Unsupervised visual domain adap-tation using subspace alignment", in Proc. IEEE International Conference on Computer vision, pp. 2960-2967, 2013. [DOI:10.1109/ICCV.2013.368]
12. [12] M. Ghifary, D. Balduzzi, W. B. Kleijn, and M. Zhang, "Scatter component analysis: A unified framework for domain adaptation and domain generalizayion", IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1-1, 2016.
13. [13] B. Sun and K. Saenko, "Subspace distribution alignment for unsupervised domain adaptation", in Proc. British Machine Vision Conference, 2015. [DOI:10.5244/C.29.24]
14. [14] J. Tahmoresnezhad and S. Hashemi, "Visual domain adaptation via transfer feature learning", Knowledge and Information Systems, vol. 50, no. 2, pp. 585-605, 2017. [DOI:10.1007/s10115-016-0944-x]
15. [15] X. Li, M. Fang, J. J. Zhang and J. Wu, "Sample selection for visual domain adaptation via sparse coding", Signal Processing: Image Communi-cation, vol. 44, pp. 92-100, 2016. [DOI:10.1016/j.image.2016.03.009]
16. [16] K. Saenko, B. Kulis, M. Fritz and T. Darrell, "Adapting visual category models to new domains", Proceedings of the European Con-ference on Computer Vision, pp. 213-226, 2010. [DOI:10.1007/978-3-642-15561-1_16]
17. [17] G.Griffin, A. Holub and P. Perona, "Caltech-256 object category dataset", Technical Report7694, 2007.
18. [18] J. J. Hull, "A¬", IEEE Trans. Pattern Anal. Mach. Intell, vol. 16, no. 5, pp. 550-554, 1994. [DOI:10.1109/34.291440]
19. [19] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, "Gradient-based learning applied to document recognition", Proc. IEEE, vol. 86, no. 11, pp. 2278-2324, 1998. [DOI:10.1109/5.726791]
20. [20] L. Duan, D. Xu, I.W. Tsang, "Domain adaptation from multiple sources: a domain-dependent regularization approach", IEEE Trans. Neural Netw. Learn. Syst, vol. 23, no. 3, pp. 504-518, 2012. [DOI:10.1109/TNNLS.2011.2178556] [PMID]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
