ELASTIC: Improving CNNs with Instance Specific Scaling Policies

@article{Wang2018ELASTICIC,
  title={ELASTIC: Improving CNNs with Instance Specific Scaling Policies},
  author={Huiyu Wang and Aniruddha Kembhavi and Ali Farhadi and Alan Loddon Yuille and Mohammad Rastegari},
  journal={CoRR},
  year={2018},
  volume={abs/1812.05262}
}
Scale variation has been a challenge from traditional to modern approaches in computer vision. Most solutions to scale issues have similar theme: a set of intuitive and manually designed policies that are generic and fixed (e.g. SIFT or feature pyramid). We argue that the scale policy should be learned from data. In this paper, we introduce ELASTIC, a simple, efficient and yet very effective approach to learn instance-specific scale policy from data. We formulate the scaling policy as a non… CONTINUE READING
13
Twitter Mentions

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 40 REFERENCES

Aggregated Residual Transformations for Deep Neural Networks

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

Densely Connected Convolutional Networks

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

CondenseNet: An Efficient DenseNet Using Learned Group Convolutions

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 1 EXCERPT

Deep Layer Aggregation

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 2 EXCERPTS

Squeeze-and-Excitation Networks

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 2 EXCERPTS

Dilated Residual Networks

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…