Multi-Dimensional Recurrent Neural Networks

TL;DR

This paper introduces multi-dimensional recurrent neural networks (MDRNNs) to extend RNN capabilities to multi-dimensional data, enabling applications in vision and medical imaging while addressing scaling issues.

Contribution

The paper presents MDRNNs, a novel extension of RNNs for multi-dimensional data, overcoming previous scalability limitations and broadening application scope.

Findings

Effective in image segmentation tasks

Addresses scaling problems of multi-dimensional models

Potential applications in vision and medical imaging

Abstract

Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition. Some of the properties that make RNNs suitable for such tasks, for example robustness to input warping, and the ability to access contextual information, are also desirable in multidimensional domains. However, there has so far been no direct way of applying RNNs to data with more than one spatio-temporal dimension. This paper introduces multi-dimensional recurrent neural networks (MDRNNs), thereby extending the potential applicability of RNNs to vision, video processing, medical imaging and many other areas, while avoiding the scaling problems that have plagued other multi-dimensional models. Experimental results are provided for two image segmentation tasks.