AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Pruning Filter in Filter

Fanxu Meng, Hao Cheng, Ke Li, Huixiang Luo, Xiaowei Guo, Guangming Lu, Xing Sun

NeurIPS 2020 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 3 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
Stripe-wise pruning (SWP) instead of group-wise pruning, same Skeleton (ablation)ResNet56 · CIFAR-10accuracy at equal params/FLOPsImproved
Stripe-wise instead of group-wise pruning (ablation)ResNet56 · CIFAR-10pruning ratio before a layer is fully removed: 76.64% -> 87.36%Improved
Train only the Filter Skeleton with fixed filter weights (ablation)VGG16 · CIFAR-10test accuracy: 79.83No clear effect
Train only the Filter Skeleton with fixed filter weights (ablation)ResNet56 · CIFAR-10test accuracy: 83.82No clear effect
Train only the Filter Skeleton with fixed filter weights (ablation)MobileNetV2 · CIFAR-10test accuracy: 83.52No clear effect
Increase alpha from 0.8e-5 to 1.4e-5 at delta 0.05 (ablation)SWP ResNet56 · CIFAR-10accuracy: 92.73 -> 92.12Hurt
Increase delta from 0.01 to 0.09 at alpha 1e-5 (ablation)SWP ResNet56 · CIFAR-10params (M): 0.45 -> 0.12Improved
Increase delta from 0.01 to 0.09 at alpha 1e-5 (ablation)SWP ResNet56 · CIFAR-10accuracy: 93.25 -> 91.83Mixed
Increase delta from 0.01 to 0.09 at alpha 1e-5 (ablation)SWP ResNet56 · CIFAR-10FLOPs (M): 111.68 -> 29.72Improved
Apply SWP after Network SlimmingVGG16 · CIFAR-10FLOPs: 1.44 -> 1.09Improved
Apply SWP after DCPVGG19 · CIFAR-10FLOPs: 10.36 -> 3.40Improved
Apply SWP after GBNResNet56 · CIFAR-10FLOPs: 0.30 -> 0.24Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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