Deep structured features for semantic segmentation

  title={Deep structured features for semantic segmentation},
  author={Michael Tschannen and Lukas Cavigelli and Fabian Mentzer and Thomas Wiatowski and Luca Benini},
  journal={2017 25th European Signal Processing Conference (EUSIPCO)},
We propose a highly structured neural network architecture for semantic segmentation with an extremely small model size, suitable for low-power embedded and mobile platforms. Specifically, our architecture combines i) a Haar wavelet-based tree-like convolutional neural network (CNN), ii) a random layer realizing a radial basis function kernel approximation, and iii) a linear classifier. While stages i) and ii) are completely pre-specified, only the linear classifier is learned from data. We… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 27 times over the past 90 days. VIEW TWEETS