AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Dynamic Network Pruning with Interpretable Layerwise Channel Selection

Yulong Wang, Xiaolu Zhang, Xiaolin Hu, Bo Zhang, Hang Su

AAAI 2020 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 43 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
dynamic discrete channel-selection pruning vs best static/dynamic baselines (VGG16-BN, ~50% MACs)VGG16-BN · CIFAR10accuracy: 93.03% (FBS) -> 93.45%Improved
increase number of actions from 1 (static) to 5 in decision unit (ablation)ResNet56 · CIFAR10MACs ratio (%) (lower better): 62.68 -> 47.38Improved
increase number of actions beyond 5 up to 10 (ablation)ResNet56 · CIFAR10accuracy: 92.57 -> 92.00Hurt
vary action number m (1 to 10) (ablation)VGG16-BN · CIFAR10accuracy: 93.38 (m=1) vs 93.45 (m=5)No clear effect
discrete decision features with tree classifiers vs Mahalanobis detectoradversarial detection (ResNet-34) · CIFAR10 CWAUROC (%): 95.85 -> 99.27Improved
decision features with GBDT vs Mahalanobis detectoradversarial detection (ResNet-34) · CIFAR10 DeepFoolAUROC (%): 91.53 -> 91.44No clear effect
decision features with GBDT vs Mahalanobis detectoradversarial detection (ResNet-34) · CIFAR100 DeepFoolAUROC (%): 83.93 -> 81.03Hurt

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