Hybrid Cosine Based Convolutional Neural Networks
This addresses efficiency challenges for deploying CNNs on resource-constrained devices like mobile phones and smart cameras, though it appears incremental as it modifies existing layers rather than introducing a new paradigm.
The paper tackles the computational and storage limitations of CNNs for embedded devices by introducing a Hybrid Cosine Based Convolution layer, which achieves similar or better performance than VGG and ResNet on classification tasks while reducing parameters and enabling faster convergence.
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.