Back to Search Start Over

Harmonic Networks with Limited Training Samples

Authors :
Ulicny, Matej
Krylov, Vladimir A
Dahyot, Rozenn
Ulicny, Matej
Krylov, Vladimir A
Dahyot, Rozenn
Publication Year :
2019

Abstract

Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter parameters. Alternative strategies have been deployed for reducing the number of parameters and / or filters to be learned and thus decrease overfitting. In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs. In this work we examine the performance of harmonic networks in limited training data scenario. We validate experimentally that its performance compares well against scattering networks that use wavelets as preset filters.

Details

Database :
OAIster
Notes :
text, Ulicny, Matej and Krylov, Vladimir A and Dahyot, Rozenn (2019) Harmonic Networks with Limited Training Samples. 2019 27th European Signal Processing Conference (EUSIPCO). pp. 1-5. ISSN 2076-1465, English
Publication Type :
Electronic Resource
Accession number :
edsoai.on1309002367
Document Type :
Electronic Resource