AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle

Song Guo, Lei Zhang, Xiawu Zheng, Yan Wang, Yuchao Li, Fei Chao, Chenglin Wu, Shengchuan Zhang, Rongrong Ji

ICCV 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 31 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
use Gaussian kernel instead of linear kernel in HSIC Lasso (ablation)APIB · CIFAR-10 VGG-16, 66% FLOPstop-1 accuracy: 92.39% -> 93.83%Improved
use Gaussian kernel instead of sigmoid kernel (ablation)APIB · CIFAR-10 VGG-16, 66% FLOPstop-1 accuracy: 86.13% -> 93.83%Improved
use Laplacian kernel instead of Gaussian kernel (ablation)APIB · CIFAR-10 VGG-16, 66% FLOPstop-1 accuracy: 93.83% -> 93.93%No clear effect
use Gaussian kernel instead of linear kernel (ablation)APIB · CIFAR-10 ResNet-56, 54% FLOPstop-1 accuracy: 93.39% -> 93.92%Improved
set channel threshold Omega to 5 instead of 10 at 95% sparsity (ablation)APIB · CIFAR-10 VGG-16top-1 accuracy: 0.39% higher accuracyImproved
set channel threshold Omega to 3 instead of 1 at 85% pruning (ablation)APIB · CIFAR-10 ResNet-56top-1 accuracy: 0.3% performance improvementImproved
set Omega to 0 (ablation)APIB · CIFAR-10top-1 accuracy: layer collapse, model non-functionalHurt
increase sample size used in pruning beyond 256 (ablation)APIB · CIFAR-10 ResNetsselected filters and accuracy: unchanged above 256No clear effect
replace real data with random images (data-free) (ablation)APIB · CIFAR-10 VGG-16, 60% prunedtop-1 accuracy: 94.08% -> 94.04%No clear effect
replace real data with random images (data-free) (ablation)APIB · ImageNet ResNet-50, 76% prunedtop-1 accuracy: 70.67% -> 70.76%No clear effect
use APIB instead of L1 norm criterion without fine-tuningVGG-16 · CIFAR-10 post-training, 10% sparsityaccuracy: 83.18 -> 92.44Improved
use APIB instead of Hrank without fine-tuningVGG-16 · CIFAR-10 post-training, 30% sparsityaccuracy: 40.24 -> 91.84Improved

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