AI Paper Atlas

Research map / Optimization / Optimizers

Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

Xiao-Ming Wu, Dian Zheng, Zuhao Liu, Wei-Shi Zheng

ICCV 2023 · Optimization › Optimizers · approach: Constrained and non-backprop training · 24 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
replace identity STE with power-function ReSTE estimator (ablation)binary ResNet-20 · CIFAR-10 1W/1AAcc (%): 84.44 -> 86.75Improved
replace RBNN polynomial estimator with ReSTE (ablation)binary ResNet-20 · CIFAR-10 1W/1AAcc (%): 85.87 -> 86.75Improved
increase o_end so estimator approaches sign functionReSTE · CIFAR-10 1W/1Aestimating error vs gradient instabilityMixed
set o_end=10 instead of 3 (ablation)ReSTE ResNet-20 · CIFAR-10 1W/1AAcc (%): 86.75 -> 82.86Hurt
use ReSTE without auxiliary modules or losses instead of RBNN with rotation moduleResNet-20 Bi-Real · CIFAR-10 1W/1AAcc (%): 87.50 -> 87.92Improved
use ReSTE instead of FDA with noise adaptation moduleResNet-18 · ImageNet 1W/1ATop-1 (%): 60.20 -> 60.88Improved

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