More is Less: A More Complicated Network with Less Inference Complexity

@article{Dong2017MoreIL,
  title={More is Less: A More Complicated Network with Less Inference Complexity},
  author={Xuanyi Dong and Junshi Huang and Yi Yang and Shuicheng Yan},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={1895-1903}
}
In this paper, we present a novel and general network structure towards accelerating the inference process of convolutional neural networks, which is more complicated in network structure yet with less inference complexity. The core idea is to equip each original convolutional layer with another low-cost collaborative layer (LCCL), and the element-wise multiplication of the ReLU outputs of these two parallel layers produces the layer-wise output. The combined layer is potentially more… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 49 CITATIONS

Meta Filter Pruning to Accelerate Deep Convolutional Neural Networks

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Network Pruning via Transformable Architecture Search

  • NeurIPS 2019
  • 2019
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND

Online Filter Weakening and Pruning for Efficient Convnets

  • 2018 IEEE International Conference on Multimedia and Expo (ICME)
  • 2018
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

BlockDrop: Dynamic Inference Paths in Residual Networks

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

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

et al

O. Russakovsky, J. Deng, +7 authors M. Bernstein
  • Imagenet large scale visual recognition challenge. IJCV
  • 2015
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Wide Residual Networks

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Deep compression: Compressing deep neural networks with pruning

S. Han, H. Mao, W. J. Dally
  • trained quantization and huffman coding. ICLR
  • 2016
VIEW 2 EXCERPTS