• Computer Science
  • Published in BMVC 2018

IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks

@inproceedings{Sun2018IGCV3IL,
  title={IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks},
  author={Ke Sun and Mingjie Li and Dong Liu and Jingdong Wang},
  booktitle={BMVC},
  year={2018}
}
In this paper, we are interested in building lightweight and efficient convolutional neural networks. Inspired by the success of two design patterns, composition of structured sparse kernels, e.g., interleaved group convolutions (IGC), and composition of low-rank kernels, e.g., bottle-neck modules, we study the combination of such two design patterns, using the composition of structured sparse low-rank kernels, to form a convolutional kernel. Rather than introducing a complementary condition… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 33 CITATIONS

Seesaw-Net: Convolution Neural Network With Uneven Group Convolution

VIEW 11 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

MuffNet: Multi-Layer Feature Federation for Mobile Deep Learning

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

EdgeCNN: Convolutional Neural Network Classification Model with small inputs for Edge Computing

VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

VIEW 4 EXCERPTS
CITES RESULTS & BACKGROUND
HIGHLY INFLUENCED

A Progressive Learning Framework for Unconstrained Face Recognition

VIEW 1 EXCERPT
CITES BACKGROUND

All You Need Is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification

VIEW 1 EXCERPT
CITES RESULTS

Balanced Decoupled Spatial Convolution for CNNs

References

Publications referenced by this paper.
SHOWING 1-10 OF 53 REFERENCES

Interleaved Group Convolutions

VIEW 9 EXCERPTS

Xception: Deep Learning with Depthwise Separable Convolutions

  • François Chollet
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

SSD: Single Shot MultiBox Detector

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Channel Pruning for Accelerating Very Deep Neural Networks

  • Yihui He, Xiangyu Zhang, Jian Sun
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 1 EXCERPT

Learning Transferable Architectures for Scalable Image Recognition