Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors

Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors

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...

Full description

Bibliographic Details
Main Authors: Antonio-Javier Gallego, Antonio Pertusa, Jorge Calvo-Zaragoza
Format: Article
Language:English
Published: MDPI AG 2018-10-01
Series:Applied Sciences
Subjects:
convolutional neural networks
k-nearest neighbor
hybrid approach
label noise
Online Access:https://www.mdpi.com/2076-3417/8/11/2086

Internet

https://www.mdpi.com/2076-3417/8/11/2086

Similar Items