AI Paper Atlas

Research map / Architectures and efficiency / Quantization

ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices

Xiangyu He, Zitao Mo, Ke Cheng, Weixiang Xu, Qinghao Hu, Peisong Wang, Qingshan Liu, Jian Cheng

ECCV 2020 · Architectures and efficiency › Quantization · approach: Binary neural networks · 26 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use orthogonal proxy matrix instead of random matrix (ablation)ProxyBNN ResNet18 · CIFAR-100 (from scratch)top-1 accuracy: 53.58 -> 67.17Improved
use orthogonal proxy matrix instead of MSE matrix (ablation)ProxyBNN ResNet18 · CIFAR-100 (from scratch)top-1 accuracy: 30.69 -> 67.17Improved
use orthogonal proxy matrix instead of random matrix (ablation)ProxyBNN ResNet-18 · ImageNettop-1 accuracy: 53.7 -> 58.7Improved
use orthogonal proxy matrix instead of MSE matrix (ablation)ProxyBNN ResNet-18 · ImageNettop-1 accuracy: 36.8 -> 58.7Improved
use orthogonal proxy matrix instead of random matrix (ablation)ProxyBNN WRN22 · CIFAR-10 (from scratch)top-1 accuracy: 91.24 -> 92.96Improved
minimize quantization error only (MSE basis) despite 8x smaller average quantization error than Bi-Real (ablation)ProxyBNN WRN22 · CIFAR-100top-1 accuracy: 69.73 -> 59.32Hurt
set penalty factor gamma from 0.001 to 1e-5 (ablation)ProxyBNN WRN22 · CIFAR-100error rate: 30.28 -> 28.43Improved
decrease penalty factor gamma from 1e-5 to 1e-7 (ablation)ProxyBNN WRN22 · CIFAR-100error rate: 28.43 -> 31.33Hurt
set proxy matrix learning rate to lr_w x 0.1 instead of lr_w (ablation)ProxyBNN WRN22 · CIFAR-100error rate: 30.77 -> 28.43Improved
reduce proxy matrix learning rate further to lr_w x 0.001 (ablation)ProxyBNN WRN22 · CIFAR-100error rate: 28.43 -> 31.44Hurt
use ProxyBNN instead of SiBNN with modified ResNet-18 (1-bit/1-bit)ResNet-18 (modified) · ImageNettop-1 accuracy: 59.7 -> 63.3Improved
use ProxyBNN instead of XNOR++ with ResNet-18 (1-bit/1-bit)ResNet-18 · ImageNettop-1 accuracy: 57.1 -> 58.7Improved

Later papers that compared with this method

1 later accepted paper reports ProxyBNN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy