Papers › ZeroQ: A Novel Zero Shot Quantization Framework

ZeroQ: A Novel Zero Shot Quantization Framework

1 Jan 2020CVPR 2020 6arXiv:2001.00281archive 2025-07-28

Yaohui Cai, Zhewei Yao, Zhen Dong, Amir Gholami, Michael W. Mahoney, Kurt Keutzer

Quantization is a promising approach for reducing the inference time and memory footprint of neural networks. However, most existing quantization methods require access to the original training dataset for retraining during quantization. This is often not possible for applications with sensitive or proprietary data, e.g., due to privacy and security concerns. Existing zero-shot quantization methods use different heuristics to address this, but they result in poor performance, especially when quantizing to ultra-low precision. Here, we propose ZeroQ , a novel zero-shot quantization framework to address this. ZeroQ enables mixed-precision quantization without any access to the training or validation data. This is achieved by optimizing for a Distilled Dataset, which is engineered to match the statistics of batch normalization across different layers of the network. ZeroQ supports both uniform and mixed-precision quantization. For the latter, we introduce a novel Pareto frontier based method to automatically determine the mixed-precision bit setting for all layers, with no manual search involved. We extensively test our proposed method on a diverse set of models, including ResNet18/50/152, MobileNetV2, ShuffleNet, SqueezeNext, and InceptionV3 on ImageNet, as well as RetinaNet-ResNet50 on the Microsoft COCO dataset. In particular, we show that ZeroQ can achieve 1.71% higher accuracy on MobileNetV2, as compared to the recently proposed DFQ method. Importantly, ZeroQ has a very low computational overhead, and it can finish the entire quantization process in less than 30s (0.5% of one epoch training time of ResNet50 on ImageNet). We have open-sourced the ZeroQ framework (https://github.com/amirgholami/ZeroQ).

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 (amirgholami/ZeroQ) was not harvested; the 19 samples below come from 2 community repositories.

Syntology 19 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 12 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): 19 samples from 2 repositories, 7 ran (4 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

amirgholami/ZeroQ officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
jakc4103/DFQ mentioned on GitHubpytorchMITSyntology: 17 samples, 7 ran (3 instrument-failed) · 10 unverified report
ricky40403/GDFQ mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified 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.

Code Syntology ran Syntology

19 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; 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
3ran
12unverified

Licence: 2 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 2 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. “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.

jakc4103/DFQ community (archive-listed) 17 samples, 7 ran (3 instrument-failed) · 10 unverified
conv_1x1_bn in 59 papers modeling/classification/MobileNetV2.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · a0131fb70c267a9e · report fixture: signature inp:int/0/int, oup:int/0/int · returned Sequential · level recorded 2026-09-22
conv_bn in 88 papers modeling/classification/MobileNetV2.py ran · our draft was wrong MIT (permissive) · e087cbfa1e53486d · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
group_annotation_by_class main_ssd.py ran · our draft was wrong MIT (permissive) · 1b2736c7aa8cd37f · report fixture: signature dataset:MockDataset/0/? · returned tuple · level recorded 2026-09-22
kl_categorical improve_dfq.py ran fingerprinted MIT (permissive) · d4613471df340857 · report fixture: signature p_logit:Tensor/2/float, q_logit:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-24
make_divisible in 76 papers modeling/classification/MobileNetV2.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 63ec083689f80f47 · report fixture: signature x:int/0/int, divisible_by:int/0/int · returned int · level recorded 2026-09-22
norm2 in 7 papers improve_dfq.py ran MIT (permissive) · 1392852bee3f1e32 · report fixture: signature weight:Tensor/2/float, idx:str/0/str, writer:SummaryWriter/0/?, step:int/0/int · returned Tensor · level recorded 2026-09-24
own_loss ZeroQ/distill_data.py ran fingerprinted MIT (permissive) · 9a031a3d8db6ad9f · report fixture: signature A:Tensor/2/float, B:Tensor/2/float · returned Tensor · level recorded 2026-09-24
F_interpolate utils/layer_transform.py unverified MIT (permissive) · 7c52bc4a936af24d · report
bias_absorption dfq.py unverified MIT (permissive) · 684a2e5289bf745a · report
freeze_model in 12 papers ZeroQ/utils/quantize_model.py unverified MIT (permissive) · fd76c5681f61e04a · report
getDistilData ZeroQ/distill_data.py unverified MIT (permissive) · 124d866697dbcc6d · report
getReconData ZeroQ/reconstruct_data.py unverified MIT (permissive) · 67b637e812abb57e · report
inference_all main_cls.py unverified MIT (permissive) · af3b154eb4651990 · report
quantize_model ZeroQ/utils/quantize_model.py unverified MIT (permissive) · 903f76ab6e68b9f9 · report
torch_cat utils/layer_transform.py unverified MIT (permissive) · 65d3bcff8398fcb5 · report
torch_mean utils/layer_transform.py unverified MIT (permissive) · 52f473532c7626da · report
unfreeze_model ZeroQ/utils/quantize_model.py unverified MIT (permissive) · c488fde89bf62be5 · report
ricky40403/GDFQ community (archive-listed) 2 samples, 0 ran · 2 unverified
freeze_act utils/quantize_model.py unverified MIT (permissive) · 2d0fb158879cdb79 · report
quantize_model utils/quantize_model.py unverified MIT (permissive) · 2bd35b3a888d928d · report

Tasks

Data Free QuantizationModel CompressionNeural Network CompressionQuantization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Data Free Quantization CIFAR10 ResNet-20 CIFAR10 CIFAR-10 W8A8 Top-1 Accuracy 93.94 #3 of 3 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

1x1 ConvolutionAuxiliary ClassifierAverage PoolingBatch NormalizationChannel ShuffleConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutGlobal Average PoolingGrouped ConvolutionGroupwise Point ConvolutionInception-v3Inception-v3 ModuleInverted Residual BlockLabel SmoothingMax PoolingPointwise ConvolutionRMSPropReLUResidual ConnectionShuffleNetShuffleNet BlockSoftmaxTest

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