Discriminative Autoencoders for Small Targets Detection - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Discriminative Autoencoders for Small Targets Detection

Résumé

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.
Fichier principal
Vignette du fichier
14_icpr_atr.pdf (360.65 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00996305 , version 1 (26-05-2014)

Identifiants

Citer

Sebastien Razakarivony, Frédéric Jurie. Discriminative Autoencoders for Small Targets Detection. IAPR International Conference on Pattern Recognition, Aug 2014, Stockholm, Sweden. pp.3528 - 3533, ⟨10.1109/ICPR.2014.607⟩. ⟨hal-00996305⟩
232 Consultations
2338 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More