AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Compact Neural Network via Stacking Hybrid Units

Weichao Lan, Yiu‐ming Cheung, Juyong Jiang, Zhikai Hu, Mengke Li

TPAMI 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Joint pruning and quantization · 15 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
increase unit hidden width c_h from 4 to 6 (ablation)TissueNet VGG-16 · CIFAR-100accuracy (%): 70.40 -> 71.13Improved
keep first and last blocks as normal layers (r strategy) (ablation)TissueNet ResNet-18 · CIFAR-100accuracy (%): 75.07 -> 76.56Improved
keep first and last blocks as normal layers (r strategy) (ablation)TissueNet ResNet-18 · CIFAR-10accuracy (%): 93.31 -> 94.50Improved
replace only intermediate layers (r strategy) (ablation)TissueNet VGG-19 · Tiny-ImageNettop-1 accuracy (%): 50.20 -> 53.54Improved
replace only intermediate layers (r strategy) (ablation)TissueNet ResNet-18 · CIFAR-100Computation Efficiency (CE): 2.39 -> 1.22Hurt
raise remaining FLOPs from 21% to 33% and params from 10% to 30% (ablation)TissueNet ResNet-style · CIFAR-100accuracy (%): 72.87% -> 74.51%Improved
use hybrid units (Hybrid2) instead of single unit U2 at equal FLOPs (ablation)TissueNet LeNet-5-style · MNISTaccuracy (%): 98.31 -> 98.65Improved
use hybrid units (Hybrid1) instead of single unit U1 (ablation)TissueNet LeNet-5-style · MNISTaccuracy (%): 98.61 -> 98.47No clear effect
use hybrid units (Hybrid3) instead of single unit U3 (ablation)TissueNet LeNet-5-style · MNISTaccuracy (%): 98.72 -> 98.59No clear effect
TissueNet vs pruning baselines on CETissueNet VGG-16 · CIFAR-100Computation Efficiency (CE): 1.59 -> 4.74Improved
TissueNet vs pruning baselines on CETissueNet MLP · MNISTComputation Efficiency (CE): 6.42 -> 36.06Improved
TissueNet vs CHIP on storage efficiencyTissueNet VGG-16 · CIFAR-10Storage Efficiency (SE): 7.82 -> 3.67Hurt

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