AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

An Information Theory-Inspired Strategy for Automated Network Pruning

Xiawu Zheng, Yuexiao Ma, Teng Xi, Gang Zhang, Errui Ding, Yuchao Li, Jie Chen, Yonghong Tian, Rongrong Ji

IJCV 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 31 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
integrate FPGM with ITPruner (ablation)ITPruner ResNet-56 · CIFAR-10top-1 accuracy: 93.43 -> 94.05Improved
use ITPruner layer-wise allocation instead of uniform allocation (ablation)VGG with L1 metric · CIFAR-10top-1 accuracy: 92.92 -> 94.00Improved
use ITPruner allocation instead of uniform with Snip metric (ablation)VGG · CIFAR-10top-1 accuracy: 92.67 -> 93.93Improved
swap local metric from L1 to Synflow (ablation)ITPruner VGG · CIFAR-10top-1 accuracy: 94.00 -> 93.71No clear effect
swap local metric from L1 to Snip (ablation)ITPruner VGG · CIFAR-10top-1 accuracy: 94.00 -> 93.93No clear effect
add mutual-information regularization to ResNet-20 training (ablation)ResNet-20 · CIFAR-10top-1 accuracy: 89.65 -> 92.01Improved
add MI regularization on top of weight decay (ablation)ResNet-20 · CIFAR-10top-1 accuracy: 92.13 -> 92.15No clear effect
replace evolutionary-search architecture with ITPruner architecture (ablation)VGG · CIFAR-10top-1 accuracy: 0.19No clear effect
compare ITPruner with HRank at similar FLOPs reductionVGG · CIFAR-10top-1 accuracy: 92.34 -> 94.00Improved
use ITPruner instead of AMCMobileNetV1 · ImageNettop-1 accuracy drop: 1.3 -> 0.8Improved
add distillation and extra tricks to ITPruner (ablation)ITPruner ResNet-50 · ImageNettop-1 accuracy: 75.75 -> 78.05Improved
use ITPruner instead of NViTDeiT-S · ImageNettop-1 accuracy: 82.19 -> 82.50Improved

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