AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Ningning Ma, Xiangyu Zhang, Hai-Tao Zheng, Jian Sun

ECCV 2018 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 7,645 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
use equal input/output channel width (1:1) instead of 1:12 (ablation)pointwise-conv benchmark network · Guideline 1 benchmark (GPU, x1)GPU speed (batches/sec): 748 -> 1480Improved
use 1 group instead of 8 groups in pointwise group convolution (ablation)group-conv benchmark network · Guideline 2 benchmark (GPU, x1)GPU speed (batches/sec): 634 -> 2451Improved
use 1-fragment instead of 4-fragment-series block (ablation)fragmentation benchmark · Guideline 3 benchmark (GPU, c=128)GPU speed (batches/sec): 752 -> 2446Improved
remove ReLU from bottleneck unit (ablation)bottleneck unit benchmark · Guideline 4 benchmark (GPU, c=32)GPU speed (batches/sec): 2427 -> 2672Improved
remove shortcut from bottleneck unit (ablation)bottleneck unit benchmark · Guideline 4 benchmark (GPU, c=32)GPU speed (batches/sec): 2427 -> 2647Improved
remove both ReLU and shortcut from bottleneck unit (ablation)bottleneck unit benchmark · Guideline 4 benchmark (GPU, c=32)GPU speed (batches/sec): 2427 -> 2842Improved
add squeeze-and-excitation moduleShuffleNet v2 2x · ImageNet val (~500 MFLOPs)top-1 error (%): 25.1 -> 24.6Mixed
use ShuffleNet v2 instead of ShuffleNet v1 at 50 layers50-layer network · ImageNet val (large models)top-1 error (%): 25.2 -> 22.8Improved
add extra 3x3 depthwise conv to enlarge receptive field (ShuffleNet v2*)ShuffleNet v2 · COCO minival detection (40M FLOPs backbone)mmAP (%): 22.5 -> 23.7Improved
add extra 3x3 depthwise conv to enlarge receptive field (ShuffleNet v2*)ShuffleNet v2 · COCO minival detection (500M FLOPs backbone)mmAP (%): 33.3 -> 34.2Improved
use ShuffleNet v2 backbone instead of ShuffleNet v1Light-Head RCNN · COCO minival detection (500M FLOPs backbone)mmAP (%): 32.9 -> 33.3Improved
use ShuffleNet v2 instead of MobileNet v2 at 40M FLOPssmall-model comparison · ImageNet val (~40 MFLOPs)top-1 error (%): 43.4 -> 39.7Improved

Later papers that compared with this method

5 later accepted papers report ShuffleNetV2 as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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