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.