BCNN: A Binary CNN with All Matrix Ops Quantized to 1 Bit Precision

October 01, 2020 ยท Declared Dead ยท ๐Ÿ› 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Arthur J. Redfern, Lijun Zhu, Molly K. Newquist arXiv ID 2010.00704 Category cs.LG: Machine Learning Cross-listed cs.CV Citations 16 Venue 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Last Checked 4 months ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted