In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks. The proposed network, called ReNet, replaces the ubiquitous convolution+pooling layer of the deep convolutional neural network with four recurrent neural networks that sweep horizontally and vertically in both directions across the image. We evaluate the proposed ReNet on three widely-used benchmark datasets; MNIST, CIFAR-10 and SVHN. The result suggests that ReNet is a viable alternative to the deep convolutional neural network, and that further investigation is needed.
@article{arxiv.1505.00393,
title = {ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks},
author = {Francesco Visin and Kyle Kastner and Kyunghyun Cho and Matteo Matteucci and Aaron Courville and Yoshua Bengio},
journal= {arXiv preprint arXiv:1505.00393},
year = {2015}
}