AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution

Taeho Kim, Yongin Kwon, Jemin Lee, Taeho Kim, Sangtae Ha

ECCV 2022 · Architectures and efficiency › Pruning and efficient tuning · approach: Joint pruning and quantization

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 compiler-informed tuning to CPrune pruning (ablation)CPrune · CIFAR-10 (ResNet-18, Kryo 585)FPS: 57.77 -> 93.63Improved
prune all subgraphs associated with a task instead of a single subgraph (ablation)CPrune · CIFAR-10 (ResNet-18, Kryo 585)FPS: 79.62 -> 93.63Improved
prune all associated subgraphs instead of one subgraph (accuracy) (ablation)CPrune · CIFAR-10 (ResNet-18, Kryo 585)Top-1 accuracy: 94.27% -> 94.14%No clear effect
use compiler-informed CPrune instead of NetAdapt+TVMResNet-18 · ImageNet (Kryo 385 CPU)FPS: 35.17 -> 36.92Improved
use CPrune instead of FPGM+TVMResNet-18 · ImageNet (Mali-G72 GPU)FPS: 26.62 -> 30.02Improved
use CPrune instead of AMC+TVMMobileNetV2 · ImageNet (Kryo 385 CPU)FPS: 67.62 -> 76.92Improved
use CPrune instead of AMC+TVMMobileNetV2 · ImageNet (Mali-G72 GPU)FPS: 90.58 -> 101.56Improved
apply CPrune on top of TVM auto-tuneResNet-18 · CIFAR-10 (Kryo 280 CPU)FPS: 33.82 -> 109.45Improved
apply CPrune on top of TVM auto-tuneMnasNet1.0 · ImageNet (Kryo 585 CPU)FPS: 42.92 -> 56.85Improved
pruning (PQF) before TVM compilation instead of original modelResNet-18 · ImageNet (Kryo 385 CPU)FPS: 18.86 -> 18.73No clear effect
raise accuracy requirement above 89% so pruning stops near iteration 6CPrune · ImageNet (ResNet-18, Kryo 385)FPS increase rate: 1.96 -> 1.3 timesHurt
select the fastest pruned model before compilation instead of after compiler optimizationVGG-16 pruned models · CIFAR-10 (RTX-3080)FPS: 2857 -> 205Hurt

Later papers that compared with this method

2 later accepted papers report C-PRUNE as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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