文献类型： 会议论文

第一作者： Sebastien Razakarivony

作者： Sebastien Razakarivony ¹ ; Frederic Jurie ² ;

作者机构： 1.SAGEM D.S. - SAFRAN Group, CNRS UMR 6072 - University of Caen - ENSICAEN

2.CNRS UMR 6072 - University of Caen - ENSICAEN

会议名称： International Conference on Pattern Recognition

主办单位：

页码： 3528-3533

摘要： This paper introduces the new concept of discriminative autoencoders. In contrast with the standard autoencoders - which are artificial neural networks used to learn compressed representation for a set of data - discriminative autoencoders aim at learning low-dimensional discriminant encodings using two classes of data (denoted such as the positive and the negative classes). More precisely, the discriminative autoencoders build a latent space (manifold) under the constraint that the positive data should be better reconstructed than the negative data. It can therefore be seen as a generative model of the discriminative data and hence can be used favorably in classification tasks. This new representation is validated on a target detection task, on which the discriminative autoencoders not only give better results than the standard autoencoders but are also competitive when compared to standard classifiers such as the Support Vector Machine.

分类号： TP391.41-53