On Convergence Properties of Implicit Self-paced Objective

Information Sciences

Volumn 462, Issue , 2018, Pages 132-140

  Ma, Zilu ^a   Liu, Shiqi ^a   Meng, Deyu ^a,b   Zhang, Yong ^c   Lo, SioLong ^d   Han, Zhi ^b  

^a XI'AN JIAOTONG UNIVERSITY   (China)

^b SHENYANG INSTITUTE OF AUTOMATION   (China)

^c THE FIRST AFFILIATED HOSPITAL OF XI AN JIAOTONG UNIVERSITY   (China)

^d MACAU UNIVERSITY OF SCIENCE AND TECHNOLOGY   (Macao)

Author keywords

Convergence; Machine learning; Non convex optimization; Self paced learning

Indexed keywords

CONVEX OPTIMIZATION; PATTERN RECOGNITION;

CONVERGENCE; CONVERGENCE PROPERTIES; CONVERGENCE RESULTS; LEARNING PROCESS; NONCONVEX OPTIMIZATION; OBJECTIVE FUNCTIONS; ROBUSTNESS ANALYSIS; SELF-PACED LEARNING;

LEARNING SYSTEMS;

EID: 85048390129     PISSN: 00200255     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.ins.2018.06.014     Document Type: Article

References (29)

1. Fan, Y., He, R., Liang, J., Hu, B.-G., Self-paced learning: An implicit regularization perspective. Proceedings of the AAAI, 2017, 1877–1883.
2. Han, J., Zhang, D., Cheng, G., Liu, N., Xu, D., Advanced deep-learning techniques for salient and category-specific object detection: a survey. IEEE Signal Process. Mag. 35:1 (2018), 84–100.
3. Huang, W., Gu, J., Ma, X., Li, Y., Self-paced model learning for robust visual tracking. J. Electron. Imaging, 26(1), 2017, 013016.
4. Jiang, L., Meng, D.Y., Zhao, Q., Shan, S.G., Hauptman, A., Self-paced curriculum learning. Proceedings of the AAAI, 2015.
5. Jiang, L., Meng, D., Mitamura, T., Hauptmann, A.G., Easy samples first: Self-paced reranking for zero-example multimedia search. Proceedings of the Twenty Second ACM International Conference on Multimedia, 2014, ACM, 547–556.
6. Jiang, L., Meng, D., Yu, S.-I., Lan, Z., Shan, S., Hauptmann, A., Self-paced learning with diversity. Proceedings of the Advances in Neural Information Processing Systems, 2014, 2078–2086.
7. Kumar, M.P., Packer, B., Koller, D., Self-paced learning for latent variable models. Proceedings of the Advances in Neural Information Processing Systems, 2010, 1189–1197.
8. Kumar, M.P., Turki, H., Preston, D., Koller, D., Learning specific-class segmentation from diverse data. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2011, IEEE, 1800–1807.
9. Lee, Y.J., Grauman, K., Learning the easy things first: Self-paced visual category discovery. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011, IEEE, 1721–1728.
10. Li, C., Wei, F., Yan, J., Zhang, X., Liu, Q., Zha, H., A self-paced regularization framework for multilabel learning. IEEE Trans. Neural Netw. Learn. Syst., 2017.
11. Li, C., Yan, J., Wei, F., Dong, W., Liu, Q., Zha, H., Self-paced multi-task learning. Proceedings of the AAAI, 2017, 2175–2181.
12. Liang, J., Jiang, L., Meng, D., Hauptmann, A., Learning to detect concepts from webly-labeled video data. Proceedings of the IJCAI, 2016.
13. Lin, L., Wang, K., Meng, D., Zuo, W., Zhang, L., Active self-paced learning for cost-effective and progressive face identification. IEEE Trans. Pattern Anal. Mach. Intell. 40:1 (2018), 7–19.
14. Ma, Z., Chang, X., Yang, Y., Sebe, N., Hauptmann, G.A., The many shades of negativity. IEEE Trans. Multimed. 19:7 (2017), 1558–1568.
15. Meng, D., Zhao, Q., Jiang, L., A theoretical understanding of self-paced learning. Inf. Sci. (Ny) 414 (2017), 319–328.
16. C. Mitash, K.E. Bekris, A. Boularias, A self-supervised learning system for object detection using physics simulation and multi-view pose estimation, arXiv: 1703.03347(2017).
17. K. Murugesan, J. Carbonell, Self-paced multitask learning with shared knowledge, arXiv: 1703.00977(2017).
18. Rockafellar, R.T., Wets, R.J.-B., Variational analysis. 317, 2009, Springer Science & Business Media.
19. Sangineto, E., Nabi, M., Culibrk, D., Sebe, N., Self paced deep learning for weakly supervised object detection. CoRR, abs/1605.07651, 2016.
20. Supancic, J.S., Ramanan, D., Self-paced learning for long-term tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013, 2379–2386.
21. Tang, K., Ramanathan, V., Fei-Fei, L., Koller, D., Shifting weights: adapting object detectors from image to video. Proceedings of the Advances in Neural Information Processing Systems, 2012, 638–646.
22. Vaida, F., Parameter convergence for EM and MM algorithms. Stat. Sin. 15 (2005), 831–840.
23. Yan, Y., Nie, F., Li, W., Gao, C., Yang, Y., Xu, D., Image classification by cross-media active learning with privileged information. IEEE Trans. Image Process. 18:12 (2016), 2494–2502.
24. Yang, Y., Ma, Z., Nie, F., Chang, X., Hauptmann, A.G., Multi-class active learning by uncertainty sampling with diversity maximization. Int. J. Comput. Vis. 113:2 (2015), 113–127.
25. Yue, Z., Meng, D., He, J., Zhang, G., Semi-supervised learning through adaptive Laplacian graph trimming. Image Vis. Comput., 2016.
26. Zangwill, W.I., Nonlinear programming: a unified approach, Prentice-Hall international series in management. 1969, Prentice-Hall.
27. Zhang, D., Meng, D., Han, J., Co-saliency detection via a self-paced multiple-instance learning framework. Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 2017, 865–878.
28. Zhao, Q., Meng, D., Jiang, L., Xie, Q., Xu, Z., Hauptmann, A.G., Self-paced learning for matrix factorization. Proceedings of the AAAI, 2015, 3196–3202.
29. Zhu, X., Zhang, Z., Improved self-paced learning framework for nonnegative matrix factorization. Pattern Recognit. Lett. 97 (2017), 1–7.