papers AI Learner
The Github is limit! Click to go to the new site.

Hybrid Cosine Based Convolutional Neural Networks

2019-04-03
Adrià Ciurana, Albert Mosella-Montoro, Javier Ruiz-Hidalgo

Abstract

Convolutional neural networks (CNNs) have demonstrated their capability to solve different kind of problems in a very huge number of applications. However, CNNs are limited for their computational and storage requirements. These limitations make difficult to implement these kind of neural networks on embedded devices such as mobile phones, smart cameras or advanced driving assistance systems. In this paper, we present a novel layer named Hybrid Cosine Based Convolution that replaces standard convolutional layers using cosine basis to generate filter weights. The proposed layers provide several advantages: faster convergence in training, the receptive field can be increased at no cost and substantially reduce the number of parameters. We evaluate our proposed layers on three competitive classification tasks where our proposed layers can achieve similar (and in some cases better) performances than VGG and ResNet architectures.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1904.01987

PDF

https://arxiv.org/pdf/1904.01987


Similar Posts

Comments