AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Differentiable Transportation Pruning

Yunqiang Li, Jan C. van Gemert, Torsten Hoefler, Bert Moons, Evangelos Eleftheriou, Bram-Ernst Verhoef

ICCV 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 22 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
use a single Sinkhorn iteration per step instead of many (ablation)Differentiable Transportation Pruning · CIFAR-10 ResNet-56accuracy and training costNo clear effect
train soft-mask learning instead of no pruning maskResNet-50 training on ImageNet · training overhead on A100training time overhead: ~0.5% overheadNo clear effect
learn importance scores end-to-end via optimal transport instead of L1+one-shotResNet-56 pruning · CIFAR-10 at 95% pruning ratioaccuracy (%): 82.79 -> 86.18Improved
use optimal-transport soft masks instead of GReg-1ResNet-56 pruning · CIFAR-10 at 92.5% pruning ratioaccuracy (%): 88.39 -> 88.03Hurt
use soft-mask transportation pruning instead of GReg-2 on ImageNetResNet-50 pruning · ImageNet at 3.06x speeduptop-1 accuracy (%): 73.90 -> 74.26Improved
use transportation pruning instead of ChipNet for global sparsityMobileNetV2 · CIFAR-100 at 80% sparsityaccuracy (%): 52.96 -> 68.90Improved
prune ResNet-34 with the proposed methodResNet-34 · ImageNet at 1.32x speeduptop-1 accuracy (%): 73.31 -> 74.28Improved

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