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

Vista sencilla de ítem
dc.contributor.authorKumar Roy, Swalpa
dc.contributor.authorKar, Purbayan
dc.contributor.authorPaoletti, Mercedes E.
dc.contributor.authorHaut, Juan M.
dc.contributor.authorPastor Vargas, Rafael
dc.contributor.authorRobles Gómez, Antonio
dc.date.accessioned2024-05-20T11:59:06Z
dc.date.available2024-05-20T11:59:06Z
dc.date.issued2021
dc.description.abstractNowadays, 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 .en
dc.description.versionversión final
dc.identifier.doi10.1109/ACCESS.2021.3107626
dc.identifier.issn2169-3536
dc.identifier.urihttps://hdl.handle.net/20.500.14468/12787
dc.journal.titleIEEE Access
dc.journal.volume9
dc.language.isoen
dc.publisherIEEE
dc.relation.centerE.T.S. de Ingeniería Informática
dc.relation.departmentSistemas de Comunicación y Control
dc.rightsAtribución 4.0 Internacional
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by/4.0
dc.titleSiCoDeF² Net: Siamese Convolution Deconvolution Feature Fusion Network for One-Shot Classificationes
dc.typeartículoes
dc.typejournal articleen
dspace.entity.typePublication
relation.isAuthorOfPublicationf93103de-336d-47ac-886b-e2cbd425ed87
relation.isAuthorOfPublication17556659-f434-4220-841d-aac35f492e62
relation.isAuthorOfPublication.latestForDiscoveryf93103de-336d-47ac-886b-e2cbd425ed87
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Pastor_Vargas_Rafael_SiCoDeF2Net.pdf
Tamaño:
1.69 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos y papers