Search results for: skip connections

• Residual MobileNets

  Publication

  • A. Brzeski
  • K. Grinholc
  • K. Nowodworski
  • A. Przybyłek

  - Year 2019

  As modern convolutional neural networks become increasingly deeper, they also become slower and require high computational resources beyond the capabilities of many mobile and embedded platforms. To address this challenge, much of the recent research has focused on reducing the model size and computational complexity. In this paper, we propose a novel residual depth-separable convolution block, which is an improvement of the basic...

  Full text to download in external service