Abstract
A novel relative minimum distance is introduced that allows improving the dissimilarity-based multiple instance classification. To this end, we apply a previously proposed mapping that brings closer, at least, a single instance from each positive training bag, while the negative-bags instances are driven apart. Our results show an increased classification performance on a broad type of real-world datasets.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
As indicated in [4], the complexity to estimate \(\varDelta {\varvec{G}}_k\), that is \(\mathcal {O}(M(M+n)n)\), where M is the total number of instances in the training set and n is the dimension, can be reduced to \(\mathcal {O}(M(M+n)n')\), by applying dimension reduction, such that \(n'<n\).
References
Amores, J.: Multi-instance classification: review, taxonomy and comparative study. Artif. Intell. 201, 81–105 (2013)
Chen, Y., Bi, J., Wang, J.Z.: MILES: multi-instance learning via embedded instance selection. IEEE Trans. Pattern Anal. Mach. Intell. 28(12), 1931–1947 (2006)
Cheplygina, V., Tax, D.M.J., Loog, M.: Dissimilarity-based ensembles for multiple instance learning. IEEE Trans. Neural Netw. Learn. Syst. 27(6), 1379–1391 (2016). https://doi.org/10.1109/TNNLS.2015.2424254
Guillaumin, M., Verbeek, J., Schmid, C.: Multiple instance metric learning from automatically labeled bags of faces. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 634–647. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15549-9_46
Du, R., Wu, Q., He, X., Yang, J.: MIL-SKDE: multi-instance learning with supervised kernel density estimation. Sig. Process. 93(6), 1471–1484 (2013)
Globerson, A., Roweis, S.T.: Metric learning by collapsing classes. In: NIPS, pp. 451–458 (2006)
Diene, O., Bhaya, A.: Conjugate gradient and steepest descent constant modulus algorithms applied to a blind adaptive array. Sig. Process. 90(10), 2835–2841 (2010)
Cheplygina, V., Tax, D.M.J., Loog, M.: Multi-instance learning with bag dissimilarities. Pattern Recognit. 48(1), 264–275 (2015)
Wang, J., Zucker, J.D.: Solving the multiple-instance problem: a lazy learning approach. In: Proceedings of the Seventeenth International Conference on Machine Learning, pp. 1119–1126. Morgan Kaufmann Publishers Inc. (2000)
Jin, R., Wang, S., Zhou, Z.H.: Learning a distance metric from multi-instance multi-label data. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 896–902 (2009)
Acknowledgment
This work is partially supported by “Convocatoria 567 de 2012 - Colciencias”. The authors acknowledge support to attend SISAP 2018 provided by “Convocatoria para la Movilidad Internacional de la Universidad Nacional de Colombia (UNAL) 2017–2018”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Ruiz-Muñoz, J.F., Castellanos-Dominguez, G., Orozco-Alzate, M. (2018). Relative Minimum Distance Between Projected Bags for Improved Multiple Instance Classification. In: Marchand-Maillet, S., Silva, Y., Chávez, E. (eds) Similarity Search and Applications. SISAP 2018. Lecture Notes in Computer Science(), vol 11223. Springer, Cham. https://doi.org/10.1007/978-3-030-02224-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-02224-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-02223-5
Online ISBN: 978-3-030-02224-2
eBook Packages: Computer ScienceComputer Science (R0)