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}
}
Highlight Information
We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. [...] Key Result This results in 58\(\times \) faster convolutional operations (in terms of number of the high precision operations) and 32\(\times \) memory savings. XNOR-Nets offer the possibility of running state-of-the-art networks on CPUs (rather than GPUs) in real-time. Our binary networks are simple, accurate, efficient, and work on challenging visual tasks. We evaluate our…Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 295 CITATIONS

Back to Simplicity: How to Train Accurate BNNs from Scratch?

VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

BinaryDenseNet: Developing an Architecture for Binary Neural Networks

VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Progressive Learning of Low-Precision Networks

VIEW 13 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources

VIEW 10 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

LCNN: Lookup-Based Convolutional Neural Network

VIEW 16 EXCERPTS
CITES METHODS & BACKGROUND

Learning Architectures for Binary Networks

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A PVT-robust Customized 4T Embedded DRAM Cell Array for Accelerating Binary Neural Networks

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Circulant Binary Convolutional Networks: Enhancing the Performance of 1-Bit DCNNs With Circulant Back Propagation

VIEW 4 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

DEFENSIVE TENSORIZATION: RANDOMIZED TENSOR PARAMETRIZATION

  • 2019
VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

DISCRETIZED NEURAL NETWORKS

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2015
2020

CITATION STATISTICS

  • 57 Highly Influenced Citations

  • Averaged 84 Citations per year from 2017 through 2019

  • 16% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 44 REFERENCES

Deep Residual Learning for Image Recognition

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Adam: A Method for Stochastic Optimization

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Going deeper with convolutions

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Bitwise Neural Networks

VIEW 1 EXCERPT

Darknet: Open source neural networks in c

  • J. Redmon
  • http://pjreddie.com/ darknet/
  • 2016
VIEW 2 EXCERPTS