AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Accelerate CNN via Recursive Bayesian Pruning

Yuefu Zhou, Ya Zhang, Yanfeng Wang, Qi Tian

ICCV 2019 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 64 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
prune layer by layer with inter-layer dependency (RBP) instead of all layers independently (IBP) (ablation)RBP · CIFAR10 VGG16compression rate and FLOPs reduction: 13.3x -> 39.1x CR, 2.3x -> 3.1x ... 3.5x FLOPs; error 8.3 -> 9.0Improved
apply BC layer by layer (RBC) instead of simultaneously (ablation)BC · CIFAR10 VGG16compression rate, FLOPs, error: 18.6x -> 25.7x CR, 2.6x -> 3.1x FLOPs, error 9.0 -> 9.5Mixed
use RBP instead of BC/SBP on VGG16VGG16 CIFAR10 · CIFAR10FLOPs reduction: 3.2x/2.6x -> 3.5x at error 9.0Improved
use RBP instead of DDS on VGG16VGG16 ILSVRC · ILSVRC2012FLOPs reduction and top-1 error: 4.0x -> 5.0x FLOPs, top-1 error 31.5 -> 31.6Mixed
use RBP instead of ThiNet on VGG16VGG16 ILSVRC · ILSVRC2012FLOPs reduction and top-1 error: 3.2x -> 5.0x FLOPs, top-1 error 30.2 -> 31.6Mixed
use RBP instead of CP on VGG16VGG16 ILSVRC · ILSVRC2012FLOPs and top-1 error: 4.4x -> 5.0x FLOPs, top-1 error 32.2 -> 31.6Improved
use ResNet-adaptive RRBP (skip down-sampling blocks, parallel pruning) instead of plain RBPResNet50 · ILSVRC2012top-1 error: 28.9 -> 27.0 top-1 error, 10.0 -> 9.0 top-5Improved
use RRBP instead of ThiNet-50ResNet50 · ILSVRC2012top-1 and top-5 error: 29.0 -> 27.0, 10.0 -> 9.0 at similar FLOPs (2.3x vs 2.2x)Improved
use RBP/RRBP instead of DDS(26)ResNet50 · ILSVRC2012FLOPs and top-1 error: 1.7x -> 2.3x/2.2x FLOPs; top-1 error 28.2 -> 28.9/27.0Improved
prune with RBP on GPUVGG16 ILSVRC · ILSVRC2012inference speed-up: 2.6x time, 3.6x storage, top-5 error +2.2Improved
prune ResNet50 with RRBP vs RBP on GPUResNet50 · ILSVRC2012top-5 error increase: +2.9 -> +1.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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