انطباق دامنه کرنلی و تطبیق توزیع متعادل برای طبقه‌بندی تصاویر

نوع مقاله: مقاله پژوهشی فارسی

نویسندگان

1 دانشکده مهندسی فناوری اطلاعات و کامپیوتر، دانشگاه صنعتی ارومیه، ارومیه، ایران.

2 گروه کامپیوتر، دانشگاه صنعتی ارومیه، ارومیه، ایران

چکیده

یادگیری انتقالی و انطباق دامنه از جمله راه حل‌های موثر در بهبود عملکرد طبقه‌بند‌های تصویر هستند که در آن دامنه منبع (مجموعه آموزشی) و دامنه هدف (مجموعه آزمایشی) از اختلاف توزیع احتمال قابل توجهی برخوردارند. در واقع، نظر به اینکه جمع‌آوری داده های ورودی در شرایط مختلف (مانند وضعیت نور یا درجه حرارت)، تجهیزات مختلف با ویژگی های متغیر (مانند تعداد پورت‌های ورودی یا کیفیت رزولوشن) و دیدگاه‌های مختلف (مانند ابعاد و محیط) انجام می‌شود، منجر به مسئله‌ی تغییر دامنه می‌شود. انطباق دامنه نیمه نظارت شده، راه حلی پیشتاز برای مسئله‌ی تغییر دامنه است که در آن، دامنه منبع و بخش کوچکی از دامنه هدف دارای برچسب هستند. در این مقاله انطباق دامنه کرنلی و تطبیق توزیع متعادل (KEDA) را برای انطباق دامنه‌های منبع و هدف، به صورت نیمه نظارتی پیشنهاد می‌کنیم. KEDA توپولوژی دامنه‌ها را از طریق ایجاد ماتریس لاپلاسی و از نقطه نظرهای شباهت‌ و تفاوت‌ حفظ می‌کند. علاوه بر این، KEDA توزیع شرطی و حاشیه‌ای بین دامنه‌ها را تطبیق می دهد. در نهایت، مجموع این راه حل‌ها، تابع طبقه‌بندی خوبی برای برچسب زدن تصاویر بدون برچسب نتیجه می‌دهد. روش پیشنهادی با روش‌های پیشرفته انطباق دامنه بر روی دیتاست‌های آفیس-کلتک-10 ، اعداد ، پای و کویل مقایسه شده است که نتایج، بهبود عملکرد قابل توجهی در روش پیشنهادی ما را نشان می‌دهد.

کلیدواژه‌ها


S.P. Singh and U.C. Jaiswal, “Machine Learning for Big Data: A New Perspective,” International Journal of Applied Engineering Research, Vol.13, No.5, pp.2753-2762. 2018.

M. Qiu, L. Yang, F. Ji, W. Zhao, W. Zhou, J. Huang, H. Chen, W.B. Croft, and W. Lin, “Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce,” arXiv preprint arXiv: 1806.05434. 2018.

M. Müller, A. Dosovitskiy, B. Ghanem and V. Koltun, “Driving policy transfer via modularity and abstraction,” arXiv preprint arXiv: 1804.09364. 2018.

J. Yu, M. Qiu, J. Jiang, J. Huang, S. Song, W. Chu and H. Chen, “Modelling domain relationships for transfer learning on retrieval-based question answering systems in e-commerce,” In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 682-690,  2018.

S. Latif, R. Rana, S. Younis, J. Qadir, and J. Epps, “Transfer learning for improving speech emotion classification accuracy,” arXiv preprint arXiv: 1801.06353, 2018.

A.M. Azab, J. Toth, L.S. Mihaylova and M. Arvaneh, “A review on transfer learning approaches in brain–computer interface,” Signal Processing and Machine Learning for Brain-Machine Interfaces, pp.81-98, 2018.

J. Wang, W. Feng, Y. Chen, H. Yu, M. Huang, and P.  S. Yu. "Visual domain adaptation with manifold embedded distribution alignment." In 2018 ACM Multimedia Conference on Multimedia Conference, pp. 402-410. ACM, 2018.

M. Baktashmotlagh, M.T. Harandi, B.C. Lovell, and M. Salzmann, “Unsupervised domain adaptation by domain invariant projection,” In Proceedings of the IEEE International Conference on Computer Vision, pp.769-776, 2013.

 M. Long, J. Wang, G. Ding, S.J. Pan, and S.Y. Philip, “Adaptation regularization: A general framework for transfer learning,” IEEE Transactions on Knowledge and Data Engineering, Vol.26, No.5, pp.1076-1089. 2014.

M. Arvaneh, and T. Tanaka, “Brain–computer interfaces and electroencephalogram: basics and practical issues,” Signal Processing and Machine Learning for Brain--Machine Interfaces, 2018.

A. Asgarian, P. Sobhani, J.C. Zhang, M. Mihailescu, A. Sibilia, A.B. Ashraf, and B. Taati, “A Hybrid Instance-based Transfer Learning Method,” arXiv preprint arXiv: 1812.01063. 2018.

S. Chen, F. Zhou, and Q. Liao. "Visual domain adaptation using weighted subspace alignment." In 2016 IEEE Visual Communications and Image Processing (VCIP), pp. 1-4, 2016.

N. Courty, R. Flamary, D. Tuia, and A. Rakotomamonjy, “Optimal transport for domain adaptation,” IEEE transactions on pattern analysis and machine intelligence, Vol.39, No.9, pp.1853-1865, 2017.

M. Long, J. Wang, G. Ding, J. Sun and S. YuPhilip, “Transfer feature learning with joint distribution adaptation”, IEEE international conference on computer vision, pp. 2200-2207, 2013.

J. Tahmoresnezhad and S. Hashemi, “Visual domain adaptation via transfer feature learning”, Knowledge and Information Systems, Vol.50, No.2, pp.585-605, 2016.

E. Sangineto, G. Zen, E. Ricci and N. Sebe, “We are not all equal: Personalizing models for facial expression analysis with transductive parameter transfer,” In Proceedings of the 22nd ACM international conference on Multimedia, pp. 357-366, 2014.

F. Li, S.J. Pan, O. Jin, Q. Yang, and X. Zhu, “Cross-domain co-extraction of sentiment and topic lexicons,” In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers,Vol.1, pp. 410-419, 2012.

الهه قولنجی، جعفر طهمورث نژاد "تطبیق دامنه‌های بصری با استفاده از تطبیق خصوصیات و مدل"، مجله مهندسی برق دانشگاه تبریز. جلد 49، شماره1، ، بهار 1398.

S. Rezaei, and J. Tahmoresnezhad, “Discriminative and domain invariant subspace alignment for visual tasks,” Iran Journal of Computer Science, pp.1-12, 2019.

W. Wei, D. Meng, Q. Zhao, Z. Xu, and Y. Wu, "Semi-Supervised Transfer Learning for Image Rain Removal," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3877-3886, 2019.

P. U. Diehl, and M. Cook. "Unsupervised learning of digit recognition using spike-timing-dependent plasticity." Frontiers in computational neuroscience, Vol.9, pp.99, 2015.

M. Belkin, P. Niyogi, and V. Sindhwani, “Manifold regularization: A geometric framework for learning from labeled and unlabeled examples,” Journal of machine learning research, No.Nov, pp.2399-2434. 2006.

D. Tuia, G. Camps-Valls, “Kernel manifold alignment for domain adaptation,” PLoS ONE, Vol.11, No.2, 2016.

C. Deng, H. Xiaofei, and H.Jiawei, “Semi-supervised discriminant analysis,” IEEE 11th International Conference on Computer Vision (ICCV), pp.1–7, 2007.

S. Ben-David, J. Blitzer, K. Crammer, and F. Pereira, “Analysis of representations for domain adaptation,” In Advances in neural information processing systems, pp.137–144, 2007.

K. Saenko, B. Kulis, M. Fritz and T. Darrell, “Adapting visual category models to new domains”, Proceedings of the European Conference on Computer Vision, pp. 213-226, 2010.  

G.Griffin, A. Holub and P. Perona, “Caltech-256 object category dataset”, Technical Report7694, 2007.

J. J. Hull, “A database for handwritten text recognition research”, IEEE Trans. Pattern Anal. Mach. Intell, vol. 16, no. 5, pp. 550–554, 1994.

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.

S. A. Nene, S. K. Nayar and H. Murase, “Columbia object image library (COIL-20)”, Technical Report CUCS, 1996.

T. Sim, S. Baker and M. Bsat, “The CMU pose, illumination, and expression (PIE) database”, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition, pp. 53-58, 2002.

M. Long, J. Wang, G. Ding, J. Sun, and P.S. Yu, “Transfer joint matching for unsupervised domain adaptation,” In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1410-1417, 2014.

G. Matasci, M. Volpi, M. Kanevski, L. Bruzzone, and D. Tuia, “Semi-supervised transfer component analysis for domain adaptation in remote sensing image classification,” IEEE Transactions on Geoscience and Remote Sensing, Vol.53, No.7, pp.3550-3564. 2015.

B. Gong, Y. Shi, F. Sha, and K. Grauman, “Geodesic flow kernel for unsupervised domain adaptation,” In 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp.2066-2073, 2012.

I. Jolliffe, “Principal component analysis” Wiley, vol. 2, pp. 433- 459, 2002.

J. Hoffman, E. Rodner, J. Donahue, T. Darrell and K. Saenko, “Efficient learning of domain-invariant image representations,” arXiv preprint arXiv: 1301.3224, 2013.

S. Herath, M. Harandi, and F. Porikli, “Learning an invariant hilbert space for domain adaptation,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3845-3854, 2017.

Y.H. Hubert Tsai, Y.R. Yeh, and Y.C. Frank Wang, “Learning cross-domain landmarks for heterogeneous domain adaptation,” In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.5081-5090, 2016.

W. Li, L. Duan, D. Xu and I.W. Tsang, “Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation,” IEEE Transactions on Pattern analysis and machine intelligence, Vol.36, No.6, pp.1134-1148, 2014.

L.A. Pereira, and R. da Silva Torres, “Semi-supervised transfer subspace for domain adaptation,” Pattern Recognition, Vol.75, pp.235-249, 2018.

W. Yu, X. Teng, and C. Liu, “Face recognition using discriminant locality preserving projections,” Image and Vision Computing, Vol.24, No.3, pp.239 – 248, 2006.

S. Huang, A. Elgammal, L. Huangfu, D. Yang, and X. Zhang, “Globality-locality preserving projections for biometric data dimensionality reduction,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW),  pp.15–20, 2014.

F. Nie, D. Xu, I.W.H Tsang, and C. Zhang, “Flexible manifold embedding: A framework for semi-supervised and unsupervised dimension reduction,” IEEE Transactions on Image Processing, Vol.19, No.7, pp.1921–1932, 2010.

S. Wang, J. Lu, X. Gu, H. Du and J. Yang, “Semi-supervised linear discriminant analysis for dimension reduction and classification,” Pattern Recognition, Vol.57, pp.179-189, 2016.

F. Nie, S. Xiang, Y. Jia, and C. Zhang, “Semi-supervised orthogonal discriminant analysis via label propagation,” Pattern Recognition, Vol.42, No.11, pp.2615 – 2627, 2009.

J. Tahmoresnezhad and S. Hashemi. "Transductive transfer learning via maximum margin criterion." Scientia Iranica. Transaction D, Computer Science & Engineering, Electrical, Vol.23, no.3, pp.1239, 2016.