AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Collaborative Channel Pruning for Deep Networks

Hanyu Peng, Jiaxiang Wu, Shifeng Chen, Junzhou Huang

ICML 2019 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 85 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
CCP versus DCP at similar FLOPs reduction, top-5 dropCCP · ILSVRC-12 ResNet-50top-5 accuracy drop: 0.61% -> 0.45%Improved
Add auxiliary classifier (CCP-AC) on ILSVRC-12, top-5 (ablation)CCP · ILSVRC-12 ResNet-50top-5 accuracy drop: 0.45% -> 0.33%Improved
Add auxiliary classifier (CCP-AC) on ILSVRC-12, top-1 (ablation)CCP · ILSVRC-12 ResNet-50top-1 accuracy drop: 0.94% -> 0.83%Improved
Add auxiliary classifier (CCP-AC) on CIFAR-10 (ablation)CCP · CIFAR-10 ResNet-56accuracy drop: 0.04% -> -0.19%Improved
CCP versus DCP-Adapt at 47.0% FLOPs reductionCCP · CIFAR-10 ResNet-56accuracy drop: -0.01% -> 0.04%Hurt
CCP versus DCP at ~50% FLOPs on CIFAR-10CCP · CIFAR-10 ResNet-56accuracy drop: 0.31% -> 0.08%Improved
CCP versus Channel Pruning (He et al.) on CIFAR-10CCP · CIFAR-10 ResNet-56accuracy drop: 1.00% -> 0.04%Improved
CCP versus Soft Pruning on ILSVRC-12 top-1CCP · ILSVRC-12 ResNet-50top-1 accuracy drop: 1.54% -> 0.65%Improved
Raise pruning ratio r from 0.35 to 0.40 on ILSVRC-12CCP · ILSVRC-12 ResNet-50top-1 accuracy drop: 0.65% -> 0.94%Hurt
Raise pruning ratio r from 0.35 to 0.40 on CIFAR-10CCP · CIFAR-10 ResNet-56accuracy drop: 0.04% -> 0.08%Hurt
Vary auxiliary classifier coefficient lambda from 0 to 1e-1 (r=0.35) (ablation)CCP-AC · CIFAR-10 ResNet-56accuracy dropImproved
Increase pruning ratio from 0.1 to 0.6 (ablation)CCP · CIFAR-10 ResNet-56accuracy dropMixed

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