Abstract:

In this paper, two methods for multiple instance target characterization, MI-SMF and MI-ACE, are presented. MI-SMF and MI-ACE estimate a discriminative target signature from imprecisely-labeled and mixed training data. In many applications, such as sub-pixel target detection in remotely-sensed hyperspectral imagery, accurate pixel-level labels on training data is often unavailable and infeasible to obtain. Furthermore, since sub-pixel targets are smaller in size than the resolution of a single pixel, training data is comprised only of mixed data points (in which target training points are mixtures of responses from both target and non-target classes). Results show improved, consistent performance over existing multiple instance concept learning methods on several hyperspectral sub-pixel target detection problems.

Links:

Citation:

A. Zare, C. Jiao, and T. Glenn, “Discriminative Multiple Instance Hyperspectral Target Characterization,” IEEE Trans. Pattern Anal Mach. Inteli., vol. 40, iss. 10, pp. 2342-2354, 2018. 

@Article{zare2016miace,
Author = {Zare, Alina and Jiao, Changzhe and Glenn, Taylor},
Title = {Discriminative Multiple Instance Hyperspectral Target Characterization},
Journal = {IEEE Trans. Pattern Anal. Mach. Inteli.},
Year = {2018},
volume = {40},
number = {10},
pages = {2342-2354},
month = {Oct.},
doi = {10.1109/TPAMI.2017.2756632},
}