AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

SUBP: Soft Uniform Block Pruning for 1$\times$N Sparse CNNs Multithreading Acceleration

Jingyang Xiang, Siqi Li, Jun Chen, Guang Dai, Shipeng Bai, Yukai Ma, Yong Liu

NeurIPS 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Sparse training from scratch

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
use BPAR instead of l1 norm as block pruning criterion (1x16) (ablation)1xN pruning of MobileNetV1 · ImageNet, p=50%top-1 accuracy: 69.56 -> 70.30Improved
use BPAR instead of l1 norm (1x8) (ablation)1xN pruning of MobileNetV1 · ImageNet, p=50%top-1 accuracy: 69.91 -> 70.55Improved
use BPAR instead of l1 norm (1x32) (ablation)1xN pruning of MobileNetV1 · ImageNet, p=50%top-1 accuracy: 69.54 -> 70.03Improved
use BPAR instead of l1 norm (1x8) (ablation)1xN pruning of ResNet-50 · ImageNet, p=50%top-1 accuracy: 76.15 -> 76.70Improved
use BPAR instead of l1 norm (1x16) (ablation)1xN pruning of ResNet-50 · ImageNet, p=50%top-1 accuracy: 76.25 -> 76.52Improved
use BPAR instead of l1 norm (1x32) (ablation)1xN pruning of ResNet-50 · ImageNet, p=50%top-1 accuracy: 75.96 -> 76.31Improved
increase block size N from 2 to 32 with l1 norm (ablation)1xN pruning of MobileNetV1 · ImageNet, p=50%top-1 accuracy: 70.28 -> 69.54Hurt
increase block size N from 16 to 32SUBP on ResNet-50 (1.0G) · ImageNet valtop-1 accuracy: 76.3% -> 76.0%Hurt
use 1x32 instead of 1x16 blocksSUBP on MobileNetV1 (279M) · ImageNet valtop-1 accuracy: 70.8% -> 71.1%Improved
filter pruning instead of weight pruningpre-trained MobileNetV1 at p=50% · ImageNettop-1 accuracy: 70.76 -> 65.35Hurt
initialize SUBP from pre-trained weights (90+120 epochs) instead of scratch (250 epochs) (ablation)SUBP(1x16) ResNet-18 · ImageNet valtop-1 accuracy: 69.9% -> 69.5%Hurt
sparse 2.0G ResNet-50 backbone vs dense backboneFaster R-CNN · COCOmAP: 37.4 -> 38.5Improved

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