Multiple-Instance Classification via Generalized Eigenvalue Proximal SVM
The multiple-instance classification problem is formulated using a linear or nonlinear kernel as the minimization of a linear function in a finite dimensional real space subject to linear and bilinear constraints by SVM-based methods. This paper presents a new multiple-instance classifier that determines two nonparallel planes by solving generalized eigenvalue proximal SVM. Our method converges in a few iterations to a local solution. Computational results on a number of datasets indicate that the proposed algorithm is competitive with the other SVM-based methods in multiple-instance classification.
H. Wang, B.J. Zhang, X.Z. Liu, D.Z. Luo, S.B. Zhong
Z. Wang and D. M. Li, "Multiple-Instance Classification via Generalized Eigenvalue Proximal SVM", Advanced Materials Research, Vols. 143-144, pp. 1235-1239, 2011