SiCoDeF² Net: Siamese Convolution Deconvolution Feature Fusion Network for One-Shot Classification

Kumar Roy, Swalpa, Kar, Purbayan, Paoletti, Mercedes E., Haut, Juan M., Pastor-Vargas, Rafael y Robles-Gómez, Antonio . (2021) SiCoDeF² Net: Siamese Convolution Deconvolution Feature Fusion Network for One-Shot Classification. IEEE Access, vol. 9, pp. 118419-118434, 2021

Ficheros (Some files may be inaccessible until you login with your e-spacio credentials)
Nombre Descripción Tipo MIME Size
Pastor_Vargas_Rafael_SiCoDeF2Net.pdf Pastor Vargas_Rafael_SiCoDeF2Net.pdf application/pdf 1.68MB

Título SiCoDeF² Net: Siamese Convolution Deconvolution Feature Fusion Network for One-Shot Classification
Autor(es) Kumar Roy, Swalpa
Kar, Purbayan
Paoletti, Mercedes E.
Haut, Juan M.
Pastor-Vargas, Rafael
Robles-Gómez, Antonio
Abstract Nowadays, deep convolutional neural networks (CNNs) for face recognition exhibit a performance comparable to human ability in the presence of the appropriate amount of labelled training data. However, training CNNs remains as an arduous task due to the lack of training samples. To overcome this drawback, applications demand one-shot learning to improve the obtained performances over traditional machine learning approaches by learning representative information about data categories from few training samples. In this context, Siamese convolutional network ( SiConvNet ) provides an interesting deep architecture to tackle the data limitation. In this regard, applying the convolution operation on real world images by using the trainable correlative Gaussian kernel adds correlations to the output images, which hinder the recognition process due to the blurring effects introduced by the convolution kernel application. As a result the pixel-wise and channel-wise correlations or redundancies could appear in both single and multiple feature maps obtained by a hidden layer. In this sense, convolution-based models fail to generalize the feature representation because of both the strong correlations presence in neighboring pixels and the channel-wise high redundancies between different channels of the feature maps, which hamper the effective training. Deconvolution operation helps to overcome the shortcomings that limit the conventional SiConvNet performance, learning successfully correlation-free features representation. In this paper, a simple but efficient Siamese convolution deconvolution feature fusion network ( SiCoDeF 2 Net ) is proposed to learn the invariant and discriminative complementary features generated from both the (i) sub-convolution (SCoNet) and (ii) sub deconvolutional (SDeNet) networks using a concatenation operation which significantly improves the one-shot unconstrained facial recognition task. Extensive experiments performed on several widely used benchmarks, provide promising results, where the proposed SiCoDeF 2 Net model significantly outperforms the current state-of-art in terms of classification accuracy, F1, precision and recall. The code will be available on: https://github.com/purbayankar/SiCoDeF2Net .
Editor(es) IEEE
Fecha 2021
Formato application/pdf
Identificador bibliuned:DptoSCC-ETSI-Articulos-Rpastor-00010
http://e-spacio.uned.es/fez/view/bibliuned:DptoSCC-ETSI-Articulos-Rpastor-00010
DOI - identifier 10.1109/ACCESS.2021.3107626
ISSN - identifier 2169-3536
Nombre de la revista IEEE Access
Número de Volumen 9
Publicado en la Revista IEEE Access, vol. 9, pp. 118419-118434, 2021
Idioma eng
Versión de la publicación acceptedVersion
Tipo de recurso Article
Derechos de acceso y licencia http://creativecommons.org/licenses/by/4.0
info:eu-repo/semantics/openAccess
Tipo de acceso Acceso abierto
Notas adicionales The registered version of this article, first published in IEEE Access, is available online at the publisher's website: IEEE, https://doi.org/10.1109/ACCESS.2021.3107626

 
Versiones
Versión Tipo de filtro
Contador de citas: Google Scholar Search Google Scholar
Estadísticas de acceso: 36 Visitas, 11 Descargas  -  Estadísticas en detalle
Creado: Tue, 30 Jan 2024, 22:31:19 CET