Next Article in Journal
Inactivation Kinetics of Salmonella typhimurium and Staphylococcus aureus in Different Media by Dielectric Barrier Discharge Non-Thermal Plasma
Previous Article in Journal
A Comparison of Empirical Procedures for Fatigue Damage Prediction in Instrumented Risers Undergoing Vortex-Induced Vibration
Article Menu
Issue 11 (November) cover image

Export Article

Open AccessArticle
Appl. Sci. 2018, 8(11), 2086; https://doi.org/10.3390/app8112086

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

1
Pattern Recognition and Artificial Intelligence Group, Department of Software and Computing Systems, University of Alicante, 03690 Alicante, Spain
2
PRHLT Research Center, Universitat Politècnica de València, 46022 Valencia, Spain
*
Author to whom correspondence should be addressed.
Received: 6 October 2018 / Revised: 23 October 2018 / Accepted: 25 October 2018 / Published: 28 October 2018
Full-Text   |   PDF [446 KB, uploaded 8 November 2018]   |  

Abstract

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 2 norm on neural codes is statistically beneficial for this approach. View Full-Text
Keywords: convolutional neural networks; k-nearest neighbor; hybrid approach; label noise convolutional neural networks; k-nearest neighbor; hybrid approach; label noise
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Gallego, A.-J.; Pertusa, A.; Calvo-Zaragoza, J. Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors. Appl. Sci. 2018, 8, 2086.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Appl. Sci. EISSN 2076-3417 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top