Siamese Multi-layer Perceptrons for Dimensionality Reduction and Face Identification - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Multimedia Tools and Applications Année : 2015

Siamese Multi-layer Perceptrons for Dimensionality Reduction and Face Identification

Résumé

This paper presents a framework using siamese Multi-layer Percep-trons (MLP) for supervised dimensionality reduction and face identification. Compared with the classical MLP that trains on fully labeled data, the siamese MLP learns on side information only, i.e., how similar of data examples are to each other. In this study, we compare it with the classical MLP on the problem of face identification. Experimental results on the Extended Yale B database demonstrate that the siamese MLP training with side information achieves comparable classification performance with the classical MLP training on fully labeled data. Besides, while the classical MLP fixes the dimension of the output space, the siamese MLP allows flexible output dimension, hence we also apply the siamese MLP for visualization of the dimensionality reduction to the 2-d and 3-d spaces.
Fichier principal
Vignette du fichier
mtap_smlp_R1.1.pdf (479.84 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01182273 , version 1 (31-07-2015)

Identifiants

Citer

Lilei Zheng, Stefan Duffner, Khalid Idrissi, Christophe Garcia, Atilla Baskurt. Siamese Multi-layer Perceptrons for Dimensionality Reduction and Face Identification. Multimedia Tools and Applications, 2015, pp.,. ⟨10.1007/s11042-015-2847-3⟩. ⟨hal-01182273⟩
407 Consultations
1871 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More