AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Distribution-Sensitive Information Retention for Accurate Binary Neural Network

Haotong Qin, Xiangguo Zhang, Ruihao Gong, Yifu Ding, Yi Xu, Xianglong Liu

IJCV 2022 · Architectures and efficiency › Quantization · approach: Binary neural networks · 144 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 IMB (information maximized binarization) (ablation)binary ResNet-20 · CIFAR-10 ablation (W1/A1)accuracy: 83.8 -> 84.9Improved
add weight standardization to IMB (ablation)IMB, ResNet-20 · CIFAR-10 ablation (W1/A1)accuracy: 84.3 -> 84.9Improved
add shift-based scalars to IMB (ablation)IMB, ResNet-20 · CIFAR-10 ablation (W1/A1)accuracy: 84.6 -> 84.9Improved
add DTE (both stages) (ablation)binary ResNet-20 · CIFAR-10 ablation (W1/A1)accuracy: 83.8 -> 85.5Improved
use only stage 1 of DTE (ablation)binary ResNet-20 · CIFAR-10 ablation (W1/A1)accuracy: 83.8 -> 83.6Hurt
keep at least 10% of weights updatable (eps 10% vs 0%) (ablation)DTE stage 2 · CIFAR-10 ablation (W1/A1)accuracy: 84.9 -> 85.1Improved
add RBD with proposed loss (ablation)binary ResNet-20 · CIFAR-10 ablation (W1/A1)accuracy: 83.8 -> 86.2Improved
distill with MSE or KL instead of proposed RBD loss (ablation)RBD, ResNet-20 · CIFAR-10 ablation (W1/A1)accuracy: 86.2 -> 84.9Hurt
lower eps from 100% to 10% (ablation)DIR-Net, ResNet-20 · CIFAR-10 epsilon sweep (W1/A1)accuracy: 84.2 -> 86.8Improved
lower eps from 10% to 0% (ablation)DIR-Net, ResNet-20 · CIFAR-10 epsilon sweep (W1/A1)accuracy: 86.8 -> 86.5Hurt
combine IMB, DTE and RBD (ablation)binary ResNet-20 · CIFAR-10 ablation (W1/A1)accuracy: 83.8 -> 89.0Improved
use IMB instead of XNOR scaling (ablation)binary ResNet-20 · CIFAR-10 binarization erroraccuracy: 84.8 -> 84.9No clear effect

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