Papers › GhostNet: More Features from Cheap Operations

GhostNet: More Features from Cheap Operations

27 Nov 2019CVPR 2020 6arXiv:1911.11907archive 2025-07-28

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

Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an important characteristic of those successful CNNs, but has rarely been investigated in neural architecture design. This paper proposes a novel Ghost module to generate more feature maps from cheap operations. Based on a set of intrinsic feature maps, we apply a series of linear transformations with cheap cost to generate many ghost feature maps that could fully reveal information underlying intrinsic features. The proposed Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks. Ghost bottlenecks are designed to stack Ghost modules, and then the lightweight GhostNet can be easily established. Experiments conducted on benchmarks demonstrate that the proposed Ghost module is an impressive alternative of convolution layers in baseline models, and our GhostNet can achieve higher recognition performance (e.g. 75.7% top-1 accuracy) than MobileNetV3 with similar computational cost on the ImageNet ILSVRC-2012 classification dataset. Code is available at https://github.com/huawei-noah/ghostnet

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (huawei-noah/ghostnet) was not harvested; the 23 samples below come from 7 community repositories.

Syntology 23 code samples harvested from 7 repositories linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 23 samples from 7 repositories, 19 ran (16 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 19 samples that ran have no recorded date.

33 repositories listed; official and paper-mentioned ones first.

huawei-noah/ghostnet officialmentioned in papermentioned on GitHubtfSyntology: not harvested report
0jason000/S-GhostNet mentioned on GitHubmindsporeApache-2.0Syntology: 7 samples, 7 ran (0 instrument-failed) · 0 unverified report
0jason000/ghostnet mentioned on GitHubmindsporeApache-2.0Syntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
Ash-Lee233/ghostnet mentioned on GitHubmindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
CarloLepelaars/ghostnet_tf2 mentioned on GitHubtfMITSyntology: not harvested report
KopiSoftware/Ghost_ResNet56 mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
iamhankai/ghostnet.pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
james77777778/keras-image-models mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GhostNetV3: Exploring the Training Strategies for Compact Models (arXiv:2404.11202; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
osmr/imgclsmob mentioned on GitHubmxnetMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResNeSt: Split-Attention Networks (arXiv:2004.08955; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
ozora-ogino/efficient_backbones mentioned on GitHubpytorchMITSyntology: 7 samples, 5 ran (2 instrument-failed) · 2 unverified report
rwightman/pytorch-image-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
seermer/TensorFlow2-EfficientNetV2 mentioned on GitHubtfSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
smitheric95/MoCoViT-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
2023-MindSpore-1/ms-code-160 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-214 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-216 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code10 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code11 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code14 mindsporeSyntology: not harvested report
CV51GO/GhostNet_Megengine pytorchSyntology: not harvested report
Mind23-2/MindCode-9 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code10 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code10 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code4 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code7 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
Tennine2077/mindspore_Ghostnet mindsporeSyntology: not harvested report
code-implementation1/Code8 mindsporeSyntology: not harvested report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ecosystem/mindcv mindsporeSyntology: not harvested report
yangyucheng000/ghostnet mindsporeApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
gitlab.com/birder/birder pytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

23 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
3ran · our draft was wrong
13ran
4unverified

Licence: 5 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 7 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

0jason000/S-GhostNet community (archive-listed) 7 samples, 7 ran (0 instrument-failed) · 0 unverified
float_parameter in 36 papers src/autoaug.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 40d3c39a403ae1f7 · report fixture: signature level:int/0/int, maxval:float/0/float · returned float · level recorded 2026-09-24
gen_cfgs_1x src/big_net.py ran Apache-2.0 (permissive) · 7022c26a18d085ec · report fixture: signature layers:list/1/int, channels:list/1/int · returned list · level recorded 2026-09-24
gen_cfgs_large src/big_net.py ran Apache-2.0 (permissive) · c83dff446ca0238d · report fixture: signature layers:list/1/int, channels:list/1/int · returned list · level recorded 2026-09-24
get_lr in 91 papers src/utils.py ran Apache-2.0 (permissive) · 9dfb4495e7fb2efb · report fixture: signature lr_init:float/0/float, lr_end:float/0/float, lr_max:float/0/float, warmup_epochs:int/0/int, total_epochs:int/0/int, steps_per_epoch:int/0/int · returned ndarray · level recorded 2026-09-24
get_lr_tinynet_c src/utils.py ran Apache-2.0 (permissive) · e1258604a87c9da4 · report fixture: signature base_lr:float/0/float, total_epochs:int/0/int, steps_per_epoch:int/0/int, decay_epochs:int/0/int, decay_rate:float/0/float, warmup_epochs:float/0/float, warmup_lr_init:float/0/float, global_epoch:int/0/int · returned ndarray · level recorded 2026-09-24
int_parameter in 35 papers src/autoaug.py ran fingerprinted Apache-2.0 (permissive) · e5a370ee6856bd8d · report fixture: signature level:int/0/int, maxval:int/0/int · returned int · level recorded 2026-09-24
str2bool in 533 papers src/utils.py ran Apache-2.0 (permissive) · 2dedef59d5e447a2 · report fixture: signature value:str/0/str · returned bool · level recorded 2026-09-24
0jason000/ghostnet community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
init_group_params in 7 papers src/optim.py ran Apache-2.0 (permissive) · 698131638ff8d4ad · report fixture: signature params:list/1/Param, weight_decay:float/0/float · returned list · level recorded 2026-09-24
is_model in 24 papers src/model.py ran Apache-2.0 (permissive) · b85a6569fd4f3890 · report fixture: signature model_name:str/0/str · returned bool · level recorded 2026-09-24
model_entrypoint in 6 papers src/model.py unverified Apache-2.0 (permissive) · ac95eb88d9b993fd · report
KopiSoftware/Ghost_ResNet56 community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
cutout in 17 papers train_Ghost_ResNet56.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · ce3aa75b714c404e · report fixture: signature img:Image/0/?, hole_size:int/0/int · returned Image · level recorded, date not recorded
iamhankai/ghostnet.pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
depthwise_conv in 6 papers ghost_net.py unverified no licence file found · pointer only · 680d03183fe725d4 · report
ozora-ogino/efficient_backbones community (archive-listed) 7 samples, 5 ran (2 instrument-failed) · 2 unverified
conv1x1 in 691 papers efficient_backbones/g_ghost_regnet.py ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv1x1 in 691 papers efficient_backbones/resnet.py ran MIT (permissive) · 6f0d1921e77f5311 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-24
conv3x3 in 1,376 papers efficient_backbones/g_ghost_regnet.py ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers efficient_backbones/resnet.py ran MIT (permissive) · 7e71d6f8569b6b34 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded 2026-09-24
hard_sigmoid in 15 papers efficient_backbones/ghostnet.py ran fingerprinted MIT (permissive) · ca43d9eb44b430e5 · report fixture: signature x:Tensor/2/float, inplace:bool/0/bool · returned Tensor · level recorded 2026-09-24
conv_1x1_bn in 59 papers efficient_backbones/efficientnet_v2.py unverified MIT (permissive) · f76badd0c6766f8a · report
conv_3x3_bn in 21 papers efficient_backbones/efficientnet_v2.py unverified MIT (permissive) · 3d6f0eda22ace06f · report
seermer/TensorFlow2-EfficientNetV2 community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
round_filters in 47 papers efficientnetV2.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract fingerprinted licence of this copy not recorded · e60387e9529f63ff · report fixture: signature filters:int/0/int, multiplier:float/0/float · returned int · level recorded, date not recorded
round_repeats in 39 papers efficientnetV2.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract fingerprinted licence of this copy not recorded · 1a9d7e65e0a9fbc9 · report fixture: signature repeats:int/0/int, multiplier:float/0/float · returned int · level recorded, date not recorded
yangyucheng000/ghostnet community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_lr in 91 papers src/lr_generator.py ran Apache-2.0 (permissive) · 78ea6999b2c97419 · report fixture: signature lr_init:float/0/float, lr_end:float/0/float, lr_max:float/0/float, warmup_epochs:int/0/int, total_epochs:int/0/int, steps_per_epoch:int/0/int · returned ndarray · level recorded 2026-09-24
get_top5_acc postprocess.py ran Apache-2.0 (permissive) · fca5ffc375803fa4 · report fixture: signature top5_arg:list/1/list, gt_class:list/1/int · returned int · level recorded 2026-09-24

Tasks

Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet GhostNet ×1.3 GFLOPs 0.226 #938 of 1060 Archive leaderboard report
Image Classification ImageNet GhostNet ×1.3 Number of params 7.3M #938 of 1060 Archive leaderboard report
Image Classification ImageNet GhostNet ×1.3 Top 1 Accuracy 75.7% #938 of 1060 Archive leaderboard report
Image Classification ImageNet Ghost-ResNet-50 (s=2) GFLOPs 2.2 #961 of 1060 Archive leaderboard report
Image Classification ImageNet Ghost-ResNet-50 (s=2) Number of params 13M #961 of 1060 Archive leaderboard report
Image Classification ImageNet Ghost-ResNet-50 (s=2) Top 1 Accuracy 75% #961 of 1060 Archive leaderboard report
Image Classification ImageNet Ghost-ResNet-50 (s=4) GFLOPs 1.2 #980 of 1060 Archive leaderboard report
Image Classification ImageNet Ghost-ResNet-50 (s=4) Number of params 6.5M #980 of 1060 Archive leaderboard report
Image Classification ImageNet Ghost-ResNet-50 (s=4) Top 1 Accuracy 74.1% #980 of 1060 Archive leaderboard report
Image Classification ImageNet GhostNet ×1.0 GFLOPs 0.141 #982 of 1060 Archive leaderboard report
Image Classification ImageNet GhostNet ×1.0 Number of params 5.2M #982 of 1060 Archive leaderboard report
Image Classification ImageNet GhostNet ×1.0 Top 1 Accuracy 73.9% #982 of 1060 Archive leaderboard report
Image Classification ImageNet GhostNet ×0.5 GFLOPs 0.042 #1043 of 1060 Archive leaderboard report
Image Classification ImageNet GhostNet ×0.5 Number of params 2.6M #1043 of 1060 Archive leaderboard report
Image Classification ImageNet GhostNet ×0.5 Top 1 Accuracy 66.2% #1043 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Ghost Bottleneck, Ghost Module, GhostNet

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutFPNFaster R-CNNFocal LossGhost BottleneckGhost ModuleGhostNetGlobal Average PoolingHard SwishInverted Residual BlockKaiming InitializationMax PoolingPointwise ConvolutionRPNRandom Horizontal FlipRandom Resized CropReLUReLU6Residual BlockResidual ConnectionRetinaNetRoIPoolSGD with MomentumSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections