XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

@inproceedings{Rastegari2016XNORNetIC,
  title={XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks},
  author={Mohammad Rastegari and Vicente Ordonez and Joseph Redmon and Ali Farhadi},
  booktitle={ECCV},
  year={2016}
}
We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-WeightNetworks, the filters are approximated with binary values resulting in 32× memory saving. In XNOR-Networks, both the filters and the input to convolutional layers are binary. XNOR-Networks approximate convolutions using primarily binary operations. This results in 58× faster convolutional operations and 32× memory savings. XNOR-Nets offer the possibility… CONTINUE READING
Highly Influential
This paper has highly influenced 133 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 1,091 citations. REVIEW CITATIONS

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • The classification accuracy with a Binary-Weight-Network version of AlexNet is only 2.9% less than the full-precision AlexNet (in top-1 measure).

Citations

Publications citing this paper.
Showing 1-10 of 725 extracted citations

Adaptive Layerwise Quantization for Deep Neural Network Compression

2018 IEEE International Conference on Multimedia and Expo (ICME) • 2018
View 6 Excerpts
Highly Influenced

Exploration of Low Numeric Precision Deep Learning Inference Using Intel® FPGAs

2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM) • 2018
View 4 Excerpts
Highly Influenced

Hierarchical binary CNNs for landmark localization with limited resources

IEEE transactions on pattern analysis and machine intelligence • 2018
View 9 Excerpts
Highly Influenced

Holistic CNN Compression via Low-rank Decomposition with Knowledge Transfer.

IEEE transactions on pattern analysis and machine intelligence • 2018
View 12 Excerpts
Highly Influenced

TernaryNet: faster deep model inference without GPUs for medical 3D segmentation using sparse and binary convolutions

International Journal of Computer Assisted Radiology and Surgery • 2018
View 11 Excerpts
Highly Influenced

Accelerating low bit-width convolutional neural networks with embedded FPGA

2017 27th International Conference on Field Programmable Logic and Applications (FPL) • 2017
View 9 Excerpts
Highly Influenced

1,092 Citations

020040060020152016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 1,092 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 43 references

Deep Residual Learning for Image Recognition

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016
View 6 Excerpts
Highly Influenced

Adam: A Method for Stochastic Optimization

View 5 Excerpts
Highly Influenced

Going deeper with convolutions

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…