Highlander, T. and Rodriguez, A. (2016) Very Efficient Training of Convolutional Neural Networks Using Fast Fourier Transform and Overlap-and-Add. In: Xie, X.H., Jones, M.W. and Tam, G.K.L., Eds., Proceedings of the British Machine Vision Conference (BMVC), BMVA Press, Guildford, 160.1-160.9.
https://doi.org/10.5244/C.29.160

has been cited by the following article:

• TITLE: Development and Parallelization of an Improved 2D Moving Window Standard Deviation Python Routine for Image Segmentation Purposes

  AUTHORS: Marcos R. de A. Conceição, Luis F. F. de Mendonça, Carlos A. D. Lentini

  KEYWORDS: Digital Image Processing, Image Segmentation, Standard Deviation, Python, Machine Learning

  JOURNAL NAME: Computational Water, Energy, and Environmental Engineering, Vol.9 No.3, July 30, 2020

  ABSTRACT: Two additional features are particularly useful in pixelwise satellite data segmentation using neural networks: one results from local window averaging around each pixel (MWA) and another uses a standard deviation estimator (MWSD) instead of the average. While the former’s complexity has already been solved to a satisfying minimum, the latter did not. This article proposes a new algorithm that can substitute a naive MWSD, by making the complexity of the computational process fall from O(N2n2) to O(N2n), where N is a square input array side, and n is the moving window’s side length. The Numba python compiler was used to make python a competitive high-performance computing language in our optimizations. Our results show efficiency benchmars