Your browser doesn't support javascript.
loading
Hierarchical One-Class Model With Subnetwork for Representation Learning and Outlier Detection.
IEEE Trans Cybern ; 53(10): 6303-6316, 2023 Oct.
Article en En | MEDLINE | ID: mdl-35486564
The multilayer one-class classification (OCC) frameworks have gained great traction in research on anomaly and outlier detection. However, most multilayer OCC algorithms suffer from loosely connected feature coding, affecting the ability of generated latent space to properly generate a highly discriminative representation between object classes. To alleviate this deficiency, two novel OCC frameworks, namely: 1) OCC structure using the subnetwork neural network (OC-SNN) and 2) maximum correntropy-based OC-SNN (MCOC-SNN), are proposed in this article. The novelties of this article are as follows: 1) the subnetwork is used to build the discriminative latent space; 2) the proposed models are one-step learning networks, instead of stacking feature learning blocks and final classification layer to recognize the input pattern; 3) unlike existing works which utilize mean square error (MSE) to learn low-dimensional features, the MCOC-SNN uses maximum correntropy criterion (MCC) for discriminative feature encoding; and 4) a brand-new OCC dataset, called CO-Mask, is built for this research. Experimental results on the visual classification domain with a varying number of training samples from 6131 to 513 061 demonstrate that the proposed OC-SNN and MCOC-SNN achieve superior performance compared to the existing multilayer OCC models. For reproducibility, the source codes are available at https://github.com/W1AE/OCC.

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Diagnostic_studies / Prognostic_studies Idioma: En Revista: IEEE Trans Cybern Año: 2023 Tipo del documento: Article Pais de publicación: Estados Unidos

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Diagnostic_studies / Prognostic_studies Idioma: En Revista: IEEE Trans Cybern Año: 2023 Tipo del documento: Article Pais de publicación: Estados Unidos