Papers › BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction

BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction

10 Feb 2021ICLR 2021 1arXiv:2102.05426archive 2025-07-28

Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, Shi Gu

We study the challenging task of neural network quantization without end-to-end retraining, called Post-training Quantization (PTQ). PTQ usually requires a small subset of training data but produces less powerful quantized models than Quantization-Aware Training (QAT). In this work, we propose a novel PTQ framework, dubbed BRECQ, which pushes the limits of bitwidth in PTQ down to INT2 for the first time. BRECQ leverages the basic building blocks in neural networks and reconstructs them one-by-one. In a comprehensive theoretical study of the second-order error, we show that BRECQ achieves a good balance between cross-layer dependency and generalization error. To further employ the power of quantization, the mixed precision technique is incorporated in our framework by approximating the inter-layer and intra-layer sensitivity. Extensive experiments on various handcrafted and searched neural architectures are conducted for both image classification and object detection tasks. And for the first time we prove that, without bells and whistles, PTQ can attain 4-bit ResNet and MobileNetV2 comparable with QAT and enjoy 240 times faster production of quantized models. Codes are available at https://github.com/yhhhli/BRECQ.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2102.05426")

Code

Syntology Ran 5 of 5 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 2 samples from 1 repository, 2 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yhhhli/BRECQ officialmentioned in paperpytorch report
lilujunai/emq-series mentioned on GitHubpytorch report
mac-automl/ompq mentioned on GitHubpytorch 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

5 samples harvested; 5 ran; 2 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
1ran · fixture could not drive it

Licence: 3 of the 5 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 yhhhli/BRECQ. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

get_train_samples yhhhli/BRECQ/main_imagenet.py official repository ran · honoured contract MIT (permissive) · 57575e67b89b74e0 · report
validate_model yhhhli/BRECQ/main_imagenet.py official repository ran · honoured contract MIT (permissive) · 605b5163dc46fdad · report
accuracy identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · b0f936d4d6ae3b8c · report
conv1x1 identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · d9def42110729a85 · report
conv3x3 identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 160bb14bd76201b4 · report

Tasks

Image ClassificationObject DetectionQuantizationimage-classificationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDepthwise ConvolutionDepthwise Separable ConvolutionGlobal Average PoolingInverted Residual BlockKaiming InitializationMax PoolingPointwise ConvolutionReLUResidual BlockResidual Connection

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