ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

@inproceedings{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},
  booktitle={ECCV},
  year={2018}
}
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, while its category-wise accuracy is only 8% less. We evaluated ESPNet on… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 42 CITATIONS

DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation

Gen Li, Inyoung Yun, Jonghyun Kim, Joongkyu Kim
  • ArXiv
  • 2019
VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Structured Knowledge Distillation for Semantic Segmentation

  • CVPR 2019
  • 2019
VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

XNect : Real-time Multi-person 3 D Human Pose Estimation with a Single RGB

Camera, DUSHYANTMEHTA, +5 authors Christian Theobalt
  • 2019
VIEW 21 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera

VIEW 21 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

Real-Time Image Semantic Segmentation Networks with Residual Depth-Wise Separable Blocks

  • 2018 Joint 10th International Conference on Soft Computing and Intelligent Systems (SCIS) and 19th International Symposium on Advanced Intelligent Systems (ISIS)
  • 2018
VIEW 5 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

Adaptative Inference Cost With Convolutional Neural Mixture Models

Adria Ruiz, Jakob Verbeek
  • ArXiv
  • 2019
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Concentrated-Comprehensive Convolutions for lightweight semantic segmentation

  • ArXiv
  • 2018
VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 65 REFERENCES

Pyramid Scene Parsing Network

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Learning to Segment Breast Biopsy Whole Slide Images

  • 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2017
VIEW 8 EXCERPTS

Xception: Deep Learning with Depthwise Separable Convolutions

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Deep Residual Learning for Image Recognition

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Dilated Residual Networks

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2017
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL