Papers › "BNN - BN = ?": Training Binary Neural Networks without Batch Normalization

"BNN - BN = ?": Training Binary Neural Networks without Batch Normalization

16 Apr 2021arXiv:2104.08215archive 2025-07-28

Tianlong Chen, Zhenyu Zhang, Xu Ouyang, Zechun Liu, Zhiqiang Shen, Zhangyang Wang

Batch normalization (BN) is a key facilitator and considered essential for state-of-the-art binary neural networks (BNN). However, the BN layer is costly to calculate and is typically implemented with non-binary parameters, leaving a hurdle for the efficient implementation of BNN training. It also introduces undesirable dependence between samples within each batch. Inspired by the latest advance on Batch Normalization Free (BN-Free) training, we extend their framework to training BNNs, and for the first time demonstrate that BNs can be completed removed from BNN training and inference regimes. By plugging in and customizing techniques including adaptive gradient clipping, scale weight standardization, and specialized bottleneck block, a BN-free BNN is capable of maintaining competitive accuracy compared to its BN-based counterpart. Extensive experiments validate the effectiveness of our proposal across diverse BNN backbones and datasets. For example, after removing BNs from the state-of-the-art ReActNets, it can still be trained with our proposed methodology to achieve 92.08%, 68.34%, and 68.0% accuracy on CIFAR-10, CIFAR-100, and ImageNet respectively, with marginal performance drop (0.23%~0.44% on CIFAR and 1.40% on ImageNet). Codes and pre-trained models are available at: https://github.com/VITA-Group/BNN_NoBN.

PaperPDFCodeCode 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="2104.08215")

Code

Syntology Ran 4 of 11 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

VITA-Group/BNN_NoBN officialmentioned in papermentioned on GitHubpytorchMIT 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

11 samples harvested; 4 ran; 1 honoured the contract we drafted; 7 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.

1ran · honoured contract
2ran · our draft was wrong
1ran
7unverified

Licence: 0 of the 11 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 VITA-Group/BNN_NoBN. “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.

conv1x1 VITA-Group/BNN_NoBN/models/Qa_reactnet_18_bn.py official repository ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report
conv3x3 VITA-Group/BNN_NoBN/models/Qa_reactnet_18_bn.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
get_padding VITA-Group/BNN_NoBN/layers.py official repository ran · honoured contract fingerprinted MIT (permissive) · 73876e077d3acdf5 · report
unitwise_norm VITA-Group/BNN_NoBN/agc.py official repository ran fingerprinted MIT (permissive) · 670bc2732a11c7eb · report
binaryconv3x3 VITA-Group/BNN_NoBN/models/Qa_reactnet_18_bf.py official repository unverified MIT (permissive) · 7fbee15b94a45d5d · report
cifar100_dataloaders VITA-Group/BNN_NoBN/dataset.py official repository unverified MIT (permissive) · 5ae551aef288dd66 · report
cifar10_dataloaders VITA-Group/BNN_NoBN/dataset.py official repository unverified MIT (permissive) · 468e801161562d86 · report
conv1x1 VITA-Group/BNN_NoBN/models/Qa_reactnet_18_bf.py official repository unverified MIT (permissive) · c40fa415189b7c0a · report
conv3x3 VITA-Group/BNN_NoBN/models/Qa_reactnet_18_bf.py official repository unverified MIT (permissive) · 20f90730b09ba843 · report
get_weight VITA-Group/BNN_NoBN/layers.py official repository unverified MIT (permissive) · 846a4b93e56bfe0b · report
imagenet_dataloaders VITA-Group/BNN_NoBN/dataset.py official repository unverified MIT (permissive) · 66a7c45936102f69 · report

Tasks

Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 ReActNet-18 Percentage correct 92.08 #185 of 265 Archive leaderboard report
Image Classification CIFAR-100 ReActNet-18 Percentage correct 68.34 #181 of 211 Archive leaderboard report
Image Classification ImageNet ReActNet-A (BN-Free) Top 1 Accuracy 68.0% #1036 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

Batch Normalization

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