Papers › RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization

RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization

11 Nov 2022arXiv:2211.06088archive 2025-07-28

Chengpeng Chen, Zichao Guo, Haien Zeng, Pengfei Xiong, Jian Dong

Feature reuse has been a key technique in light-weight convolutional neural networks (CNNs) design. Current methods usually utilize a concatenation operator to keep large channel numbers cheaply (thus large network capacity) by reusing feature maps from other layers. Although concatenation is parameters- and FLOPs-free, its computational cost on hardware devices is non-negligible. To address this, this paper provides a new perspective to realize feature reuse via structural re-parameterization technique. A novel hardware-efficient RepGhost module is proposed for implicit feature reuse via re-parameterization, instead of using concatenation operator. Based on the RepGhost module, we develop our efficient RepGhost bottleneck and RepGhostNet. Experiments on ImageNet and COCO benchmarks demonstrate that the proposed RepGhostNet is much more effective and efficient than GhostNet and MobileNetV3 on mobile devices. Specially, our RepGhostNet surpasses GhostNet 0.5x by 2.5% Top-1 accuracy on ImageNet dataset with less parameters and comparable latency on an ARM-based mobile phone.

PaperPDFCodeCode 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

Syntology 17 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 10 ran (6 with no instrument failure; 4 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

chengpengchen/repghost officialmentioned in papermentioned on GitHubpytorchMITSyntology: 17 samples, 10 ran (4 instrument-failed) · 7 unverified report
rwightman/pytorch-image-models officialmentioned in papermentioned 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
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

17 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 7 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.

1ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
5ran
7unverified

Licence: 0 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from chengpengchen/repghost. “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.

chengpengchen/repghost official repository 17 samples, 10 ran (4 instrument-failed) · 7 unverified
clever_format infotool/helper.py ran; the contract check could not run (RAISES) MIT (permissive) · b161f124ff564c74 · report fixture: signature nums:list/1/float, format:str/0/str · returned tuple · level recorded 2026-09-24
colorful_print infotool/helper.py ran · our draft was wrong MIT (permissive) · 12576d42d14e9ae2 · report fixture: signature fn_print:callable/0/?, color:str/0/str · returned function · level recorded 2026-09-24
convert_syncbn_to_bn tools.py ran MIT (permissive) · 88f7445c5b1400a9 · report fixture: signature module:callable/0/? · returned TestModule · level recorded 2026-09-25
count_clamp infotool/fx_profile.py ran · honoured contract MIT (permissive) · 2878428e1958cb9a · report fixture: signature input_shapes:list/1/tuple, output_shapes:list/1/tuple · returned int · level recorded 2026-09-24
count_matmul infotool/fx_profile.py ran · our draft was wrong MIT (permissive) · 911b9807f4998259 · report fixture: signature input_shapes:list/1/Size, output_shapes:list/1/Size · returned int · level recorded 2026-09-24
count_mul infotool/fx_profile.py ran · our draft was wrong MIT (permissive) · 31618bae63672c9e · report fixture: signature input_shapes:list/1/Tensor, output_shapes:list/1/Tensor · returned int · level recorded 2026-09-24
counter_conv infotool/vision/counter.py ran MIT (permissive) · 7f32bc2caccead61 · report fixture: signature bias:int/0/int, kernel_size:int/0/int, output_size:int/0/int, in_channel:int/0/int, group:int/0/int · returned Tensor · level recorded 2026-09-25
counter_norm infotool/vision/counter.py ran fingerprinted MIT (permissive) · c1f9c3bdd753a577 · report fixture: signature input_size:int/0/int · returned Tensor · level recorded 2026-09-25
counter_parameters infotool/vision/counter.py ran MIT (permissive) · 3096fbb3cb601582 · report fixture: signature para_list:list/1/Tensor · returned Tensor · level recorded 2026-09-25
hard_sigmoid in 15 papers model/repghost.py ran fingerprinted MIT (permissive) · f9479314f0ac20b2 · report fixture: signature x:Tensor/2/float, inplace:bool/0/bool · returned Tensor · level recorded 2026-09-25
count_upsample infotool/vision/basic_hooks.py unverified MIT (permissive) · 31325cecc16666a0 · report
onnx_counter_add infotool/vision/onnx_counter.py unverified MIT (permissive) · 1f1bf8d0c1cb9792 · report
onnx_counter_conv infotool/vision/onnx_counter.py unverified MIT (permissive) · f0c18018ea33388f · report
onnx_counter_matmul infotool/vision/onnx_counter.py unverified MIT (permissive) · a0515d90835a5334 · report
repghost_model_convert model/repghost.py unverified MIT (permissive) · c8ca5c60836a3516 · report
repghostnet model/repghost.py unverified MIT (permissive) · e9cceb505126ab1b · report
validate in 313 papers validate.py unverified MIT (permissive) · 08ff6e71ddb0c3d9 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutGhost BottleneckGhost ModuleGhostNetGlobal Average PoolingHard SwishInverted Residual BlockPointwise ConvolutionReLUReLU6Residual ConnectionSigmoid ActivationSoftmaxSqueeze-and-Excitation Block

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