Improving image categorization by using multiple instance learning with spatial relation
Pages 108 - 117
Abstract
Image categorization is a challenging problem when a label is provided for the entire training image only instead of the object region. To eliminate labeling ambiguity, image categorization and object localization should be performed simultaneously. Discriminative Multiple Instance Learning (MIL) can be used for this task by regarding each image as a bag and sub-windows in the image as instances. Learning a discriminative MI classifier requires an iterative solution. In each round, positive sub-windows for the next round should be selected. With standard approaches, selecting only one positive sub-window per positive bag may limit the search space for global optimum; meanwhile, selecting all temporal positive sub-windows may add noise into learning. We select a subset of sub-windows per positive bag to avoid those limitations. Spatial relations between sub-windows are used as clues for selection. Experimental results demonstrate that our approach outperforms previous discriminative MIL approaches and standard categorization approaches.
References
[1]
Dietterich, T., Lathrop, R., Lozano-Perez, T.: Solving the Multiple-Instance Problem with Axis-Parallel Rectangles. Artificial Intelligence, 31-71 (1997).
[2]
Maronand, O., Lozano-Perez, T.: A Framework for Multiple Instance Learning. In: Advances in Neural Information Processing Systems, pp. 570-576 (1998).
[3]
Zhang, Q., Goldman, S.: EM-DD: An Improved Multiple Instance Learning Technique. In: Advances in Neural Information Processing Systems, pp. 1073-1080 (2002).
[4]
Chen, Y., Wang, J.Z.: Image Categorization by Learning and Reasoning with Regions. Journal of Machine Learning Research, 913-939 (2004).
[5]
Andrews, S., Tsochantaridi, I., Hofmann, T.: Support Vector Machines for Multiple-Instance Learning. In: Advances in Neural Information Processing Systems, pp. 561-568 (2003).
[6]
Chen, Y., Bi, J., Wang, J.: MILES: Multiple-Instance Learning via Embedded Instance Selection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1931-1947 (2006).
[7]
Fu, Z., Robles-Kelly, A.: An Instance Selection Approach to Multiple Instance Learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 911-918 (2009).
[8]
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: Workshop on Generative-Model Based Vision, IEEE Conference on Computer Vision and Pattern Recognition (2004).
[9]
Nguyen, M.H., Torresani, L., Torre, F., Rother, C.: Weakly Supervised Discriminative Localization and Classification: A Joint Learning Process. In: IEEE Conference on Computer Vision and Pattern Recognition (2009).
[10]
Galleguillos, C., Belongie, S.: Context Based Object Categorization: A Critical Survey. In: Computer Vision and Image Understanding (2010).
[11]
Marques, O., Barenholtz, E., Charvillat, V.: Context Modeling in Computer Vision: Techniques, Implications, and Applications. Journal of Multimedia Tools and Applications (2010).
[12]
Zha, Z.J., Hua, X.S., Mei, T., Wang, J., Qi, G.J., Wang, Z.: Joint Multi-Label Multi-Instance Learning for Image Classification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8 (2008).
[13]
Divvala, S.K., Hoiem, D., Hays, J.H., Efros, A., Hebert, M.: An Empirical Study of Context in Object Detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1271-1278 (2009).
[14]
Wolf, L., Bileschi, S.: A Critical View of Context. International Journal of Computer Vision (2006).
Index Terms
- Improving image categorization by using multiple instance learning with spatial relation
Recommendations
Multiple-Instance Active Learning for Image Categorization
MMM '09: Proceedings of the 15th International Multimedia Modeling Conference on Advances in Multimedia ModelingBoth multiple-instance learning and active learning are widely employed in image categorization, but generally they are applied separately. This paper studies the integration of these two methods. Different from typical active learning approaches, the ...
Multiple instance learning with bag dissimilarities
Multiple instance learning (MIL) is concerned with learning from sets (bags) of objects (instances), where the individual instance labels are ambiguous. In this setting, supervised learning cannot be applied directly. Often, specialized MIL methods ...
Multiple instance learning
The characteristics specific of MIL problems are formally identified and described.MIL methods and applications are reviewed in the light of the problem characteristics.Comparative experiments show the impact of problem characteristics on 16 reference ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 14 September 2011
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Nov 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in