AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Channel Pruning Guided by Classification Loss and Feature Importance

Jinyang Guo, Wanli Ouyang, Dong Xu

AAAI 2020 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 50 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 classification-loss guidance during channel selection (ablation)CPLI · CIFAR-10, VGGNet, 2.86× CRAccuracy change (%): +0.04 -> +0.96Improved
add feature-importance guidance to account for features removed at the next pruning stage (ablation)CPLI · CIFAR-10, VGGNet, 2.86× CRAccuracy change (%): +0.47 -> +0.96Improved
increase sampled spatial locations from 1 to 10 (ablation)CPLI · CIFAR-10, VGGNet, 2.86× CRAccuracy change (%): +0.12 -> +0.96Improved
increase sampled spatial locations from 10 to 20 (ablation)CPLI · CIFAR-10, VGGNet, 2.86× CRAccuracy change (%): +0.96 -> +0.97No clear effect
use CPLI rather than DCPVGGNet · CIFAR-10, 2.86× CRTop-1 accuracy change (%): +0.58 -> +0.96Improved
use CPLI rather than DCPResNet-56 · CIFAR-10, 1.99× CRTop-1 accuracy change (%): -0.31 -> +0.07Improved
use CPLI rather than DCPMobileNet-V2 · CIFAR-10, 1.36× CRTop-1 accuracy change (%): +0.22 -> +0.35Improved
use CPLI rather than DCPResNet-50 · ImageNet, 2.25× CRTop-5 accuracy change (%): -0.61 -> -0.38Improved
use CPLI rather than DCPMobileNet-V2 · ImageNet, 1.81× CRTop-1 accuracy change (%): -5.89 -> -4.84Improved
use CPLI rather than RBPC3D · UCF-101, 2× CRClip-level accuracy change (%): -3.56 -> -2.18Improved

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