AI Paper Atlas

Research map / Architectures and efficiency / CNN design

GhostNets on Heterogeneous Devices via Cheap Operations

Kai Han, Yunhe Wang, Chang Xu, Jianyuan Guo, Chunjing Xu, Enhua Wu, Qi Chuan Tian

IJCV 2022 · Architectures and efficiency › CNN design · approach: Efficient CNN scaling and dynamic inference · 204 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 C-Ghost bottlenecks instead of inverted residual with SE (Net-A) (ablation)C-GhostNet 0.5x · ImageNet valtop-1 accuracy (%): 64.2 -> 66.2Improved
use C-Ghost bottlenecks instead of lower resolution inverted residual (Net-B) (ablation)C-GhostNet 0.5x · ImageNet valtop-1 accuracy (%): 65.7 -> 66.2Improved
use C-Ghost bottlenecks instead of deeper inverted residual network (Net-C) (ablation)C-GhostNet 0.5x · ImageNet valtop-1 accuracy (%): 62.3 -> 66.2Improved
use C-Ghost bottlenecks instead of deeper inverted residual network (Net-D) (ablation)C-GhostNet 0.5x · ImageNet valtop-1 accuracy (%): 61.0 -> 66.2Improved
use depthwise kernel d=3 instead of d=1 in C-Ghost module (ablation)C-Ghost VGG16 · CIFAR-10 (VGG16)accuracy (%): 93.5 -> 93.7Improved
increase depthwise kernel size from d=3 to d=7 (ablation)C-Ghost VGG16 · CIFAR-10 (VGG16)accuracy (%): 93.7 -> 93.1Hurt
increase ratio s from 2 to 5 (ablation)C-Ghost VGG16 · CIFAR-10 (VGG16)accuracy (%): 93.7 -> 92.9Hurt
add mix operation (intrinsic feature aggregation) to G-Ghost stage (ablation)G-Ghost-ResNet56 · CIFAR-10 (ResNet56)accuracy (%): 93.7 -> 93.9Improved
add mix operation to G-Ghost stage (ablation)G-Ghost-RegNetX · ImageNet val (RegNetX-3.2GF)top-1 accuracy (%): 76.8 -> 77.8Improved
add mix operation to G-Ghost stage (ablation)G-Ghost-ResNet34 · ImageNet val (ResNet34)top-1 accuracy (%): 72.8 -> 73.1Improved
use 1x1 conv cheap operation instead of identity mapping (ablation)G-Ghost-ResNet56 · CIFAR-10 (ResNet56)accuracy (%): 93.3 -> 93.7Improved
use 1x1 conv cheap operation instead of removing it (ablation)G-Ghost-ResNet56 · CIFAR-10 (ResNet56)accuracy (%): 93.2 -> 93.7Improved

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