AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks

Kaixin Xu, Zhe Wang, Xue Geng, Min Wu, Xiaoli Li, Weisi Lin

ICCV 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 32 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
jointly optimize layerwise sparsity via additivity-based dynamic programming instead of single-layer optimization (ablation)layer-adaptive weight pruning · ImageNet VGG-16-BNTop-1 accuracy (%): 62.50 -> 69.01Improved
joint optimization vs single-layer on ResNet-50 (ablation)layer-adaptive weight pruning · ImageNet ResNet-50Top-1 accuracy (%): 74.89 -> 75.59Improved
add outlier filtering of rate-distortion curves (ablation)RD-based pruning · CIFAR-10 ResNet-32 (89% sparsity)Top-1 accuracy (%): 91.15 -> 91.51Improved
add worst case sampling for distortion (ablation)RD-based pruning · CIFAR-10 ResNet-32 (89% sparsity)Top-1 accuracy (%): 91.15 -> 91.31Improved
add worst case sampling for distortion (ablation)RD-based pruning · ImageNet ResNet-50 one-shot (60% sparsity)Top-1 accuracy (%): 31.22 -> 31.22No clear effect
add both WCS and OF (ablation)RD-based pruning · CIFAR-10 ResNet-32 (89% sparsity)Top-1 accuracy (%): 91.15 -> 92.3Improved
joint optimization vs LAMP at high sparsityiterative pruning · ImageNet ResNet-50 (~6% FLOPs)Top-1 accuracy (%): 42.54 -> 67.91Improved
joint optimization vs LAMP on CIFAR-10 ResNet-32 at ~3% FLOPsiterative pruning · CIFAR-10 ResNet-32Top-1 accuracy (%): 83.66 -> 90.83Improved
use white-noise data instead of real calibration data for RD curvesRD-based pruning · ImageNet ResNet-50 zero-data (50% sparsity)Top-1 accuracy (%): 75.13 (zero-data, 1.01 drop)No clear effect
joint optimization vs LAMP on ImageNet ResNet-50 at 95.5% sparsityiterative pruning · ImageNet ResNet-50Top-1 accuracy (%): 66.04 -> 66.06No clear effect
use PGMPF with better dense baseline vs ours on VGG-16 CIFAR-10iterative pruning · CIFAR-10 VGG-16 (~33% FLOPs)Top-1 accuracy (%): 93.6 vs 92.76Hurt

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