AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Multi-Granularity Pruning for Model Acceleration on Mobile Devices

Tianli Zhao, Xi Sheryl Zhang, Wentao Zhu, Jiaxing Wang, Sen Yang, Ji Liu, Jian Cheng

ECCV 2022 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 5 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 joint channel and weight search instead of weight sparsity only at ~160ms (ablation)JCW ResNet18 · ImageNetTop-1 accuracy: 68.45% -> 69.16%Improved
add joint weight pruning instead of channel width search only at ~160ms (ablation)JCW ResNet18 · ImageNetTop-1 accuracy: 66.78% -> 69.16%Improved
search channel and weight jointly instead of sequentially at ~196ms (ablation)JCW ResNet18 · ImageNetTop-1 accuracy: 69.29% -> 69.90%Improved
add joint search instead of weight sparsity only at ~196ms (ablation)JCW ResNet18 · ImageNetTop-1 accuracy: 69.54% -> 69.90%Improved
add uniform non-dominated sorting selection to the evolutionary search (ablation)JCW ResNet18 · ImageNetTop-1 accuracyImproved

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