AI Paper Atlas

Research map / Architectures and efficiency / Quantization

OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks

jingyang xiang, Zuohui Chen, Siqi Li, Qing Wu, Yong Liu

ECCV 2024 · Architectures and efficiency › Quantization · approach: Binary neural networks · 6 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
add Adaptive Gradient Scaling (AGS) (ablation)binarized ResNet18 · CIFAR100top-1 accuracy (%): 65.23 -> 69.61Improved
add Silence Awareness Decaying (SAD) (ablation)binarized ResNet18 · CIFAR100top-1 accuracy (%): 65.23 -> 69.45Improved
add SAD on top of AGS (ablation)OvSW · CIFAR100top-1 accuracy (%): 69.61 -> 69.77Improved
add OvSW as plug-and-play module to AdaBinAdaBin · CIFAR100top-1 accuracy (%): 70.56 -> 72.56Improved
add OvSW as plug-and-play module to RBNNRBNN · CIFAR100top-1 accuracy (%): 67.15 -> 69.98Improved
use OvSW instead of vanilla training for fast convergencebinarized ResNet18 · CIFAR100 (60 epochs)top-1 accuracy (%): 55.28 -> 66.37Improved
set AGS threshold lambda too small or too large (best 0.04) (ablation)AGS · CIFAR100top-1 accuracyMixed
apply OvSW to ResNet18 vs ReCUOvSW · ImageNet1Ktop-1 accuracy (%): 61.0 -> 61.6Improved
reduce silent weights fraction with OvSW (layer4.conv2)binarized ResNet18 · CIFAR100 weight flippingratio of never-flipped weights: 54.07% -> 2.03%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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