AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Discrimination-aware Network Pruning for Deep Model Compression

Jing Liu, Bohan Zhuang, Zhuangwei Zhuang, Yong Fang Guo, Junzhou Huang, Jinhui Zhu, Mingkui Tan

TPAMI 2021 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 165 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
add discrimination-aware loss (DCP vs random channel selection) (ablation)DCP · CIFAR-10 ResNet-56Top-1 error (%): 6.66 -> 6.28Improved
add discrimination-aware loss (DCP vs WM+) (ablation)DCP · CIFAR-10 VGGNetTop-1 error (%): 6.12 -> 5.71Improved
add adaptive stopping conditions (Adapt-DCP vs DCP)DCP · CIFAR-10 ResNet-56#Param. reduction (%): 49.67 -> 68.48Improved
use stopping condition 2 instead of 1 (ablation)Adapt-DCP · CIFAR-10 VGGNet (eps 1e-4)FLOPs reduction (%): 30.80 -> 69.81Improved
use stopping condition 2 instead of 1 (ablation)Adapt-DCP · CIFAR-10 ResNet-56Top-1 error (%): 6.36 -> 6.23Improved
tighten tolerance epsilon from 5e-4 to 1e-4 (ablation)Adapt-DCP · CIFAR-10 VGGNetTop-1 error (%): 6.36 -> 5.45Improved
add reconstruction loss to cross-entropy lambda weight 1 vs 0 (ablation)DCP · CIFAR-10 ResNet-56Top-1 error (%): 5.94 -> 5.80Improved
single round fine-tuning instead of conference version (ablation)DCP · CIFAR-10 ResNet-56Pruning time (hours): 7.58 -> 2.83Improved
single round fine-tuning (ablation)DCP · ILSVRC-12 ResNet-18Top-1 error (%): 35.88 -> 35.89No clear effect
add feature reusing (ablation)DCP · CIFAR-10 ResNet-56Top-1 error (%): 6.26 -> 6.28No clear effect
increase B from 1 to 4 (ablation)DCP · CIFAR-10 ResNet-56Top-1 error (%): 6.22 -> 6.32Mixed
add DKP kernel pruning to DCPDCP · CIFAR-10 ResNet-56Top-1 error (%): 6.28 -> 6.23Improved

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