no code implementations • 29 Jul 2022 • R. J. Cintra, S. Duffner, C. Garcia, A. Leite
The idea is to approximate all elements of a given ConvNet and replace the original convolutional filters and parameters (pooling and bias coefficients; and activation function) with efficient approximations capable of extreme reductions in computational complexity.
no code implementations • 8 Aug 2018 • R. S. Oliveira, R. J. Cintra, F. M. Bayer, T. L. T. da Silveira, A. Madanayake, A. Leite
Practical applications in image and video coding demonstrate the relevance of the proposed transformation.