Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation
Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (The Swiss AI Lab IDSIA)
arXiv:1506.07452 [cs.CV], (24 Jun 2015)
@article{stollenga2015parallel,
title={Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation},
author={Stollenga, Marijn F. and Byeon, Wonmin and Liwicki, Marcus and Schmidhuber, Juergen},
year={2015},
month={jun},
archivePrefix={"arXiv"},
primaryClass={cs.CV}
}
Convolutional Neural Networks (CNNs) can be shifted across 2D images or 3D videos to segment them. They have a fixed input size and typically perceive only small local contexts of the pixels to be classified as foreground or background. In contrast, Multi-Dimensional Recurrent NNs (MD-RNNs) can perceive the entire spatio-temporal context of each pixel in a few sweeps through all pixels, especially when the RNN is a Long Short-Term Memory (LSTM). Despite these theoretical advantages, however, unlike CNNs, previous MD-LSTM variants were hard to parallelize on GPUs. Here we re-arrange the traditional cuboid order of computations in MD-LSTM in pyramidal fashion. The resulting PyraMiD-LSTM is easy to parallelize, especially for 3D data such as stacks of brain slice images. PyraMiD-LSTM achieved best known pixel-wise brain image segmentation results on MRBrainS13 (and competitive results on EM-ISBI12).
June 26, 2015 by hgpu
