AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Linearly Replaceable Filters for Deep Network Channel Pruning

Donggyu Joo, Eojindl Yi, Sunghyun Baek, Junmo Kim

AAAI 2021 · Architectures and efficiency › CNN design · approach: CNN filter pruning · 33 citations (OpenAlex)

Read the paper

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
select filters by linear replaceability and compensate remaining weights when pruningResNet on CIFAR-10 · CIFAR-10accuracy: LRF-50: 92.49 -> 92.54; LRF-60: 92.49 -> 92.02Improved
select filters by linear replaceability and compensate remaining weights when pruningResNet-50 · ImageNetTop-1 accuracy: 75.71Improved
add Weights Compensation to LRF rather than removing channels without changing remaining weights (ablation)ResNet-56 · CIFAR-10, last convolution layeroutput feature-map differenceImproved
use LRF pruning instead of training the pruned architecture from scratch (ablation)ResNet-56 · CIFAR-10accuracy: 89.85 -> 93.73; 91.44 -> 93.73Improved
use LRF pruning instead of training the pruned architecture from scratch (ablation)ResNet-56 · CIFAR-10accuracy: 89.81 -> 93.19; 91.13 -> 93.19Improved
vary the baseline model's accuracy while applying the same pruning method (ablation)LRF on ResNet-56 · CIFAR-10pruned accuracy: 93.13 (± 0.14); 93.18 (± 0.13); 93.27 (± 0.11); 93.16 (± 0.15)No clear effect
evaluate pruning by accuracy drop alone rather than final pruned accuracynetwork-pruning comparisons · CIFAR-10, ResNet-56pruned accuracyNo clear effect

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