AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Disentangled Differentiable Network Pruning

Shangqian Gao, Feihu Huang, Yanfu Zhang, Heng Huang

ECCV 2022 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 16 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 disentangled width/importance pruning vs Gumbel-sigmoid differentiable pruning baseline (ablation)DDNP · CIFAR-10 ResNet-56accuracy during pruning: advantage obvious at p = 0.35 and p = 0.5Improved
use soft top-k (smoothstep) instead of hard top-k (gamma = 0) (ablation)DDNP · CIFAR-10 ResNet-56accuracy during pruning: gap around 5% at large pruning rateImproved
use GRU+FC importance generator instead of FC only or per-channel scores (ablation)DDNP · CIFAR-10 ResNet-56accuracy during pruningImproved
use sigmoid output for gs instead of absolute or square function (ablation)DDNP · CIFAR-10 ResNet-56accuracy during pruningImproved
DDNP vs DCP pruning at similar FLOPsDDNP · CIFAR-10 ResNet-56Delta-Acc: 0.20% better than DCPImproved
DDNP vs GFS on MobileNetV2DDNP · ImageNet MobileNetV2Top-1: 0.60%/0.65% higherImproved
DDNP vs GFS on MobileNetV3 smallDDNP · ImageNet MobileNetV3 smallTop-1: 1.23%/1.06% betterImproved
DDNP vs CC on ResNet-50DDNP · ImageNet ResNet-50Delta Top-1: improves GBN and CC by 0.43% and 0.32%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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