Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/82698
Título: | Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors |
---|---|
Autor/es: | Gallego, Antonio-Javier | Pertusa, Antonio | Calvo-Zaragoza, Jorge |
Grupo/s de investigación o GITE: | Reconocimiento de Formas e Inteligencia Artificial |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos |
Palabras clave: | Convolutional neural networks | k-nearest neighbor | Hybrid approach | Label noise |
Área/s de conocimiento: | Lenguajes y Sistemas Informáticos |
Fecha de publicación: | 28-oct-2018 |
Editor: | MDPI |
Cita bibliográfica: | Gallego A-J, Pertusa A, Calvo-Zaragoza J. Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors. Applied Sciences. 2018; 8(11):2086. doi:10.3390/app8112086 |
Resumen: | We present a hybrid approach to improve the accuracy of Convolutional Neural Networks (CNN) without retraining the model. The proposed architecture replaces the softmax layer by a k-Nearest Neighbor (kNN) algorithm for inference. Although this is a common technique in transfer learning, we apply it to the same domain for which the network was trained. Previous works show that neural codes (neuron activations of the last hidden layers) can benefit from the inclusion of classifiers such as support vector machines or random forests. In this work, our proposed hybrid CNN + kNN architecture is evaluated using several image datasets, network topologies and label noise levels. The results show significant accuracy improvements in the inference stage with respect to the standard CNN with noisy labels, especially with relatively large datasets such as CIFAR100. We also verify that applying the ℓ2 norm on neural codes is statistically beneficial for this approach. |
Patrocinador/es: | This work was supported by the Spanish Ministerio de Ciencia, Innovación y Universidades through the HISPAMUS project (Ref. TIN2017-86576-R, partially funded by UE FEDER funds). |
URI: | http://hdl.handle.net/10045/82698 |
ISSN: | 2076-3417 |
DOI: | 10.3390/app8112086 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/article |
Derechos: | © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
Revisión científica: | si |
Versión del editor: | https://doi.org/10.3390/app8112086 |
Aparece en las colecciones: | INV - GRFIA - Artículos de Revistas |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
2018_Gallego_etal_ApplSci.pdf | 417,07 kB | Adobe PDF | Abrir Vista previa | |
Este ítem está licenciado bajo Licencia Creative Commons