Abstract
In this paper, we address the problem of image annotation when the given labels of training image are incomplete, inaccurate, and unevenly distributed, in the form of weak labels, which is frequently encountered when dealing with large scale web image training set. We introduce a progressive semantic neighborhood learning approach that explicitly addresses the challenge of learning from weakly labeled image by searching image’s semantic consistent neighborhood. Neighbors in image’s semantic consistent neighborhood have global similarity, partial correlation, conceptual similarity along with semantic balance. We also present an efficient label inference algorithm to handle noise by minimizing the neighborhood reconstruction error. Experiments with different data sets show that the proposed framework is more effective than the state-of-the-art algorithms in dealing with weakly labeled datasets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Makadia, A., Pavlovic, V., Kumar, S.: A new baseline for image annotation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 316–329. Springer, Heidelberg (2008)
Nguyen, N.: Classification with partial labels. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 551–559. ACM Press, New York (2008)
He, X.: Learning hybrid models for image annotation with partially labeled data. In: Conference on Neural Information Processing Systems, pp. 625–632 (2008)
Fan, J.: Harvesting large-scale weakly-tagged image databases from the web. In: International Conference on Computer Vision, pp. 802–809. IEEE Computer Society Press, Los Alamitos (2010)
Bucak, S.: Multi-label learning with incomplete class assignments. In: International Conference on Computer Vision, pp. 2801–2808. IEEE Computer Society Press, Los Alamitos (2011)
Shwartz, S.: Pegasos: Primal estimated sub-gradient solver for svm. In: International Conference on Machine Learning, pp. 807–814 (2007)
Saad, Y.: Gmres: A generalized minimal residual algorithm for solving nonsymmetric linear systems. In: International Conference on Computer Vision; SIAM Journal on Scientific and Statistical Computing 7, 856–869 (1986)
Carneiro, G.: Supervised learning of semantic classes for image tagging and retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence 29, 394–410 (2007)
Guillaumin, M.: Tagprop: Discriminative Metric Learning in Nearest Neighbor Models for Image Auto-tagging. In: International Conference on Computer Vision, pp. 309–316. IEEE Computer Society Press, Los Alamitos (2009)
Zhang, S.: Automatic image annotation using group sparsity. In: International Conference on Computer Vision, pp. 3312–3319. IEEE Computer Society Press, Los Alamitos (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tian, F., Shen, X. (2013). Image Annotation with Weak Labels. In: Wang, J., Xiong, H., Ishikawa, Y., Xu, J., Zhou, J. (eds) Web-Age Information Management. WAIM 2013. Lecture Notes in Computer Science, vol 7923. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38562-9_38
Download citation
DOI: https://doi.org/10.1007/978-3-642-38562-9_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38561-2
Online ISBN: 978-3-642-38562-9
eBook Packages: Computer ScienceComputer Science (R0)