AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Denoised Variance-Based Pruning with Optimal Brain Bias Compensation

Geon Tack Lee, Choo Jaegul, Kang Eun Jeon

ECCV 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 0 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 denoised variance scoring (Marchenko-Pastur) to VBP (ablation)VBP · most DeiT/Swin/ConvNeXt modelsTop-1 accuracy: gains of 1-2%Improved
add denoised variance scoring (ablation)VBP · DeiT-S and Swin-BTop-1 accuracy: decrease of less than 1%No clear effect
add OB2C weight update to VBP (ablation)VBP · DeiT-TTop-1 accuracy: nearly 14% absoluteImproved
add OB2C weight update to VBP (ablation)VBP · remaining modelsTop-1 accuracy: 4-7%Improved
use DVBP + OB2C instead of VBP at higher pruning ratioVBP · Swin-STop-1 accuracy gap: 2.28% at 40% -> 7.33% at 50% -> 25.49% at 60%Improved
use DVBP + OB2C instead of VBPVBP · ConvNeXt-TTop-1 accuracy: +29.46%Improved
use DVBP + OB2C instead of VBPVBP · ConvNeXt-BTop-1 accuracy: +14.64%Improved
add denoising and OB2C pass over VBPVBP · pruning timetime: approximately 2x VBP; 66.92 seconds on Swin-BHurt

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