AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps

Alireza Ganjdanesh, Shangqian Gao, Heng Huang

ECCV 2022 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning

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 RBF-style mask parameterization instead of independent per-pixel masks (ablation)ISP · CIFAR-10 ResNet-56test accuracyImproved
use larger gamma_1 interpretation weight (instead of 0.1) (ablation)ISP · CIFAR-10 ResNet-56test accuracy stabilityImproved
use small gamma_2 FLOPs regularization weight (1.0) (ablation)ISP · CIFAR-10 ResNet-56test accuracyMixed
add classification loss to interpretation-only objective (ablation)ISP · CIFAR-10 ResNet-56test accuracyImproved
add interpretation term to classification-loss-only objective (ablation)ISP · CIFAR-10 ResNet-56test accuracyImproved
replace EEMC with ISPEEMC · CIFAR-10 ResNet-56delta accuracy: +0.06% -> +0.18%Improved
replace DCP with ISPDCP · CIFAR-10 MobileNetV2delta accuracy: +0.22% -> +0.32%Improved
replace FPGM with ISPFPGM · ImageNet ResNet-34delta Top-1: -1.29% -> -0.45%Improved
replace EEMC with ISPEEMC · ImageNet ResNet-50delta Top-1: -0.49% -> -0.16%Improved
replace QI with ISPQI · ImageNet ResNet-101delta Top-1: -2.31% -> +0.40%Improved
replace MetaPruning with ISPMetaPruning · ImageNet MobileNet-V2delta Top-1: -0.80% -> -0.15%Improved

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