Zare Alina, Jiao Changzhe, Glenn Taylor
IEEE Trans Pattern Anal Mach Intell. 2018 Oct;40(10):2342-2354. doi: 10.1109/TPAMI.2017.2756632. Epub 2017 Sep 26.
In this paper, two methods for discriminative 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.
本文提出了两种用于判别式多示例目标表征的方法，即MI-SMF和MI-ACE。MI-SMF和MI-ACE从不精确标记的混合训练数据中估计判别式目标特征。在许多应用中，如遥感高光谱图像中的亚像素目标检测，训练数据上准确的像素级标签通常不可用且难以获得。此外，由于亚像素目标的尺寸小于单个像素的分辨率，训练数据仅由混合数据点组成（其中目标训练点是目标类和非目标类响应的混合）。结果表明，在几个高光谱亚像素目标检测问题上，与现有的多示例概念学习方法相比，性能有了改进且具有一致性。
