AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

UPSCALE: Unconstrained Channel Pruning

Alvin Wan, Hanxiang Hao, Kaushik Patnaik, Yueyang Xu, Omer Hadad, David Güera, Zhile Ren, Qi Shan

ICML 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 0 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
remove channel-pruning constraints (unconstrained pruning) and export with UPSCALEpost-training pruned models, averaged across heuristics and sparsity levels · ImageNettop-1 accuracy: +2.1 points on averageImproved
remove constraints (unconstrained pruning)DenseNet121 post-training pruned models · ImageNettop-1 accuracy: +16.9 points on averageImproved
remove constraints on EfficientNetV2-Small with LAMP at higher sparsityEfficientNetV2-Small LAMP · ImageNet post-trainingtop-1 accuracy: 78.7% vs 11.4% at 10%; 3.8% vs 0.1% at 30%Improved
remove constraints (unconstrained pruning) with ResNet18 smaller modelResNet18 post-training pruning · ImageNettop-1 accuracy: -0.8 pointsHurt
export unconstrained-pruned models with UPSCALE reordering instead of baseline memory-copy export (ablation)exported model latency across heuristics and architectures · ImageNet models latency benchmarklatency reduction: 8.6% average; up to 52.8% at a specific sparsity (ResNet18, FPGM)Improved
prune multi-branch segments in addition to single-branch segments (using UPSCALE export) (ablation)MobileNetV3-Small with fine-tuning · ImageNet FLOPs-accuracy tradeofftop-1 accuracy at matched compression: 59.32 vs 55.33 at 10%Improved
export unconstrained-pruned models without UPSCALE (baseline memory copies) on DenseNet121 HRank (ablation)DenseNet121 latency · ImageNet latencylatency (ms): 5.93 vs 5.44 ms at 1% sparsity for UPSCALE; baseline latency above unpruned ~1.1ms claim is for MobileNetV3-SmallHurt

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