Computation and Memory Efficient Image Segmentation

@article{Zhou2018ComputationAM,
  title={Computation and Memory Efficient Image Segmentation},
  author={Yiren Zhou and Thanh-Toan Do and Haitian Zheng and Ngai-Man Cheung and Lu Fang},
  journal={IEEE Transactions on Circuits and Systems for Video Technology},
  year={2018},
  volume={28},
  pages={46-61}
}
In this paper, we address the segmentation problem under limited computation and memory resources. Given a segmentation algorithm, we propose a framework that can reduce its computation time and memory requirement simultaneously, while preserving its accuracy. The proposed framework uses standard pixel-domain downsampling and includes two main steps. Coarse segmentation is first performed on the downsampled image. Refinement is then applied to the coarse segmentation results. We make two novel… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-6 OF 6 CITATIONS

Fine-Grained Wound Tissue Analysis Using Deep Neural Network

  • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2018
VIEW 1 EXCERPT
CITES BACKGROUND

On classification of distorted images with deep convolutional neural networks

  • 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2017
VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 39 REFERENCES

Efficient Graph-Based Image Segmentation

  • International Journal of Computer Vision
  • 2004
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Contour Detection and Hierarchical Image Segmentation

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2011
VIEW 21 EXCERPTS
HIGHLY INFLUENTIAL

Introduction to algorithms [2nd ed.]

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Normalized Cuts and Image Segmentation

  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 2000
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Spectral segmentation with multiscale graph decomposition

  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Segmentation and boundary detection using multiscale intensity measurements

  • Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Fast multiscale image segmentation

  • Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)
  • 2000
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL