AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Exploring Structural Sparsity of Deep Networks Via Inverse Scale Spaces

Yanwei Fu, Chen Liu, Donghao Li, Zuyuan Zhong, Xinwei Sun, Jinshan Zeng, Yuan Yao

TPAMI 2022 · Architectures and efficiency › Pruning and efficient tuning · approach: Sparse training from scratch · 14 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 momentum and weight decay to DessiLBI (ablation)DessiLBI · ImageNet-2012 ResNet-18top-1 accuracy (%): 65.26 -> 70.55Improved
add momentum to DessiLBI (ablation)DessiLBI · ImageNet-2012 ResNet-18top-1 accuracy (%): 65.26 -> 68.55Improved
DessiLBI Mom-Wd instead of SGD Mom-WdDessiLBI · ImageNet-2012 ResNet-18top-1 accuracy (%): 69.76 -> 70.55Improved
DessiLBI Mom-Wd instead of SGD Mom-WdDessiLBI · ImageNet-2012 AlexNettop-1 accuracy (%): 56.55 -> 57.09Improved
DessiLBI Mom-Wd instead of SGD NesterovDessiLBI · ImageNet-2012 ResNet-18top-1 accuracy (%): 70.19 -> 70.55Improved
fine-tuning instead of retraining pruned structure (ablation)DessiLBI · CIFAR10 weight pruning VGG16sparse accuracy (%): 93.60 -> 94.18Improved
fine-tuning instead of retraining pruned structure (ablation)DessiLBI · CIFAR10 filter pruning ResNet56sparse accuracy (%): 93.15 -> 93.94Improved
fine-tune only 10 epochs instead of full fine-tuning (ablation)DessiLBI · CIFAR10 filter pruning ResNet56sparse accuracy (%): 93.94 -> 89.97Hurt
pruning layers (layer selection) instead of filter pruning (ablation)DessiLBI · CIFAR10 ResNet56sparse accuracy (%): MFLOP 78 (62%) -> 56 (45%); accuracy 93.94 -> 93.47Mixed
DessiLBI filter pruning vs HRankDessiLBI · CIFAR10 VGG16sparse accuracy (%): 93.43 -> 93.59 (FT 200)Mixed
DessiLBI weight pruning vs Iterative-Pruning-B at sparsity 0.10DessiLBI · CIFAR10 ResNet50sparse accuracy (%): 73.75 -> 92.64Improved
early stopped DessiLBI for winning tickets vs one-shot and iterative pruningDessiLBI · CIFAR10 winning ticketsaccuracyImproved

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