AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Filter Pruning via Feature Discrimination in Deep Neural Networks

Zhiqiang He, Yaguan Qian, Yuqi Wang, Bin Wang, Xiaohui Guan, Zhaoquan Gu, Xiang Ling, Shaoning Zeng, Haijiang Wang, Wujie Zhou

ECCV 2022 · Architectures and efficiency › CNN design · approach: CNN filter 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 distinguishing layer pruning instead of global threshold pruning (ablation)RFC criterion (VGG16) · CIFAR-10accuracy (%): 92.25 -> 93.38Improved
add distinguishing layer pruning instead of global threshold pruning (ablation)RFC criterion (VGG16) · CIFAR-100accuracy (%): 71.25 -> 73.82Improved
add distinguishing layer pruning instead of global threshold pruning (ablation)L1 criterion (VGG16) · CIFAR-10accuracy (%): 90.56 -> 93.12Improved
add distinguishing layer pruning instead of global threshold pruning (ablation)L1 criterion (VGG16) · CIFAR-100accuracy (%): 70.90 -> 73.49Improved
add distinguishing layer pruning instead of global threshold pruning (ablation)BN scale (NS) criterion (VGG16) · CIFAR-10accuracy (%): 92.64 -> 93.25Improved
add distinguishing layer pruning instead of global threshold pruning (ablation)BN scale (NS) criterion (VGG16) · CIFAR-100accuracy (%): 71.12 -> 73.55Improved
use RFC criterion instead of L1 within distinguishing layer pruning (ablation)DLP (VGG16) · CIFAR-10accuracy (%): 93.12 -> 93.38Improved
use RFC criterion instead of NS within distinguishing layer pruning (ablation)DLP (VGG16) · CIFAR-10accuracy (%): 93.25 -> 93.38Improved
use RFC criterion instead of L1 within distinguishing layer pruning (ablation)DLP (VGG16) · CIFAR-100accuracy (%): 73.49 -> 73.82Improved
use RFC criterion instead of NS within distinguishing layer pruning (ablation)DLP (VGG16) · CIFAR-100accuracy (%): 73.55 -> 73.82Improved
use RFC instead of NS under global threshold pruning (ablation)GTP (VGG16) · CIFAR-10accuracy (%): 92.64 -> 92.25Hurt
use RFC instead of L1 under global threshold pruning (ablation)GTP (VGG16) · CIFAR-10accuracy (%): 90.56 -> 92.25Improved

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