-
[pdf]
[arXiv]
[bibtex]@InProceedings{Redfern_2021_CVPR, author = {Redfern, Arthur J. and Zhu, Lijun and Newquist, Molly K.}, title = {BCNN: A Binary CNN With All Matrix Ops Quantized to 1 Bit Precision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {4604-4612} }
BCNN: A Binary CNN With All Matrix Ops Quantized to 1 Bit Precision
Abstract
This paper describes a CNN where all CNN style 2D convolution operations that lower to matrix matrix multiplication are fully binary. The network is derived from a common building block structure that is consistent with a constructive proof outline showing that binary neural networks are universal function approximators. 71.24% top 1 accuracy on the 2012 ImageNet validation set was achieved with a 2 step training procedure and implementation strategies optimized for binary operands are provided.
Related Material