A small helper framework for training binary networks is available on github and can be installed using pip or conda:
| Using pip | Using conda |
|---|---|
pip install bnn |
conda install -c 1adrianb bnn |
For more details regarding usage and features please visit the repository page.
Note: Code for the "High-Capacity Expert Binary Networks" paper is available here.
Binary Neural Networks (BNNs) are neural networks whose convolutional and/or linear layers are operating using data represented on a single bit. Note, that typically not all operations are binary and current approaches make use of full precision normalization layers. Thanks to binarization, layers quantized to such degree can replace all their multiplications with bitwise operations while the weights themselves can be compressed to a factor of x32 via bit-packing.
@inproceedings{bulat2021bit,
title={Bit-Mixer: Mixed-precision networks with runtime bit-width selection},
author={Bulat, Adrian and Tzimiropoulos, Georgios},
booktitle={International Conference on Computer Vision},
year={2021}
}
@inproceedings{bulat2021high,
title={High-Capacity Expert Binary Networks},
author={Bulat, Adrian and Martinez, Brais and Tzimiropoulos, Georgios},
booktitle={International Conference on Learning Representations (ICLR)},
year={2021}
}
@inproceedings{bulat2020bats,
title={BATS: Binary ArchitecTure Search},
author={Bulat, Adrian and Martinez, Brais and Tzimiropoulos, Georgios},
booktitle={European Conference on Computer Vision (ECCV)},
year={2020}
}
@incollection{martinez2020training,
title={Training binary neural networks with real-to-binary convolutions},
author={Martinez, Brais and Yang, Jing and Bulat, Adrian and Tzimiropoulos, Georgios},
booktitle={ICLR},
year={2020}
}
@inprocessings{bulat2019xnor-net-plus,
title={XNOR-Net++: Improved binary neural networks},
author={Bulat, Adrian and Tzimiropoulos, Georgios},
booktitle={British Machine Vision Conference},
year={2016}
}
@article{bulat2018hierarchical,
title={Hierarchical binary CNNs for landmark localization with limited resources},
author={Bulat, Adrian and Tzimiropoulos, Georgios},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2018}
}
@inproceedings{bulat2017binarized,
title={Binarized convolutional landmark localizers for human pose estimation and face alignment with limited resources},
author={Bulat, Adrian and Tzimiropoulos, Georgios},
booktitle={The IEEE International Conference on Computer Vision (ICCV)},
volume={1},
number={2},
pages={4},
year={2017}
}