ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

@article{Mehta2018ESPNetES,
  title={ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation},
  author={Sachin Mehta and Mohammad Rastegari and Anat Caspi and Linda G. Shapiro and Hannaneh Hajishirzi},
  journal={CoRR},
  year={2018},
  volume={abs/1803.06815}
}
We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a new convolutional module, efficient spatial pyramid (ESP), which is efficient in terms of computation, memory, and power. ESPNet is 22 times faster (on a standard GPU) and 180 times smaller than the state-of-the-art semantic segmentation network PSPNet [1], while its categorywise accuracy is only 8% less. We evaluated ESPNet… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 18 times over the past 90 days. VIEW TWEETS