AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Variance-Based Pruning for Accelerating and Compressing Trained Networks

Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache

ICCV 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 7 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 mean-shift compensation to variance-based pruning (ablation)VBP · ImageNet DeiT-B 50%accuracy retained before fine-tuning: 26.04 -> 66.40 (retention); 80.62 -> 80.99 (final)Improved
use variance-based selection instead of random-like selection (keep mean-shift) (ablation)VBP · ImageNet DeiT-B 50%top-1 accuracy: 80.23 -> 80.99 (final); 55.19 -> 66.40 (retention)Improved
measure variance after the activation instead of before (ablation)VBP · ImageNet DeiT-B 50%top-1 accuracy: 77.92 -> 80.99 (final); 0.43 -> 66.40 (retention)Improved
use variance criterion instead of SNIPstructured one-shot pruning · ImageNet DeiT-B 50%top-1 accuracy: 80.40 -> 80.99 (final); 53.24 -> 66.40 (retention)Improved
use variance criterion instead of Magnitudestructured one-shot pruning · ImageNet DeiT-B 50%top-1 accuracy: 78.88 -> 80.99 (final); 0.37 -> 66.40 (retention)Improved
use variance criterion instead of SNIPstructured one-shot pruning · ImageNet DeiT-T 50%top-1 accuracy: 69.10 -> 70.61 (final); 24.89 -> 39.58 (retention)Improved
apply VBP on top of ToMe with smaller token reduction instead of larger ToMe reductionToMe on DeiT-B · ImageNettop-1 accuracy: 75.74 -> 80.09 (final) at about 2x speed-upImproved
use VBP instead of NViT with the same 1-epoch pruningNViT Base · ImageNettop-1 accuracy: 81.92 -> 82.32 (final); 69.10 -> 72.37 (retention)Improved
use VBP with 1 epoch instead of NViT with 50 epochs of pruningNViT Base · ImageNettop-1 accuracy: 82.18 -> 82.32 (final)Improved
lower DeiT-B pruning rate from 55% to 20% (ablation)VBP · ImageNet DeiT-Btop-1 accuracy before fine-tuning: 57.58 -> 80.87 (retention)Improved
apply VBP to ConvNeXt instead of transformersVBP · ImageNetaccuracy retained before fine-tuning: 16.80 (ConvNeXt-T) vs 64.44 (DeiT-S)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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