AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration

Zhengang Li, Geng Yuan, Wei Niu, Pu Zhao, Yanyu Li, Yuxuan Cai, Xuan Shen, Zheng Zhan, Zhenglun Kong, Qing Jin, Zhiyu Chen, Sijia Liu and 4 more

CVPR 2021 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 32 citations (OpenAlex)

Check 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 NPAS with compiler-aware joint architecture search and pruningImageNet classification models · ImageNetTop-1 accuracy: 78.2 vs. 75.2Improved
Use NPAS with compiler-aware joint architecture search and pruningImageNet classification models · ImageNet on Galaxy S10 GPUlatency: 6.7msImproved
Use the proposed compiler optimizations instead of MNNMobileNet-V3 · MobileNet-V3 inference on mobile CPU and GPUinference speedup: 46% and 141%Improved
Use block-punched pruning rather than unstructured pruning (ablation)ResNet-50 · ImageNet, uniform 6× pruninglatencyImproved
Use unstructured pruning rather than block-punched pruning (ablation)ResNet-50 · ImageNet, uniform 6× pruningaccuracyImproved
Replace the original ResNet-50 with a narrower model having twice as many layers at the same MACs (ablation)ResNet-50 · Mobile GPU inferencelatency: 1.22× slower (44ms vs. 36ms)Hurt
Replace mobile-unfriendly activations with hard-sigmoid and hard-swish (ablation)Pretrained DNN models · ImageNetaccuracyNo clear effect
Choose 3×3 convolution filters rather than 1×1 filters at equal computation (ablation)Convolution layers · Mobile CPU, input feature map 56×56latencyImproved
Use pattern-based or block-punched fine-grained pruning rather than unstructured pruning (ablation)3×3 convolution layer · Mobile CPU, pruning rates below 5×speedupImproved
Use pattern-based or block-punched fine-grained pruning rather than coarse-grained structured pruning (ablation)3×3 convolution layer · Mobile CPU, pruning rates below 5×speedupMixed

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