Papers › CBAM: Convolutional Block Attention Module

CBAM: Convolutional Block Attention Module

17 Jul 2018ECCV 2018 9arXiv:1807.06521archive 2025-07-28

Sanghyun Woo, Jongchan Park, Joon-Young Lee, In So Kweon

We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, our module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement. Because CBAM is a lightweight and general module, it can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs. We validate our CBAM through extensive experiments on ImageNet-1K, MS COCO detection, and VOC 2007 detection datasets. Our experiments show consistent improvements in classification and detection performances with various models, demonstrating the wide applicability of CBAM. The code and models will be publicly available.

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

Syntology 22 code samples harvested from 6 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 9 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): 22 samples from 6 repositories, 13 ran (10 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

AndrzejMiskow/FER-with-Attention-and-Objective-Activation-Functions mentioned on GitHubtfSyntology: not harvested report
HaloTrouvaille/YOLO-Multi-Backbones-Attention mentioned on GitHubpytorchSyntology: not harvested report
JinLi711/Attention-Augmented-Convolution mentioned on GitHubtfSyntology: not harvested report
JinLi711/Convolution_Variants mentioned on GitHubtfSyntology: not harvested report
Knight825/models-pytorch mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
LKLQQ/CBAM mentioned on GitHubmindsporeApache-2.0Syntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
Nithesh5/torch-adni-bagging-with-attentional mentioned on GitHubpytorchSyntology: not harvested report
Nithesh5/torch-adni-bootstrap-with-attentional mentioned on GitHubpytorchSyntology: not harvested report
TooTouch/WhiteBox-Part1 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Visualizing and Understanding Convolutional Networks (arXiv:1311.2901; that paper's own run record: 2 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; 0 where Syntology's instrument failed) · 2 unverified), Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization (arXiv:1610.02391; that paper's own run record: 90 ran (of which 32 constructed an object rather than computing a result; 62 with no instrument failure: 6 honoured, 4 violated, 52 with no contract checked; 28 where Syntology's instrument failed) · 51 unverified) and Axiomatic Attribution for Deep Networks (arXiv:1703.01365; that paper's own run record: 36 ran (of which 13 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 1 violated, 17 with no contract checked; 15 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
Uranium-Deng/Steganalysis-StegoRemoval mentioned on GitHubpytorchSyntology: not harvested report
YONGQUAN-QU/CBAM.Flax mentioned on GitHubjaxSyntology: not harvested report
e96031413/AA-YOLO mentioned on GitHubpytorchSyntology: not harvested report
e96031413/PyTorch_YOLOv4-tiny mentioned on GitHubpytorchSyntology: not harvested report
gan3sh500/custom-pooling mentioned on GitHubpytorchSyntology: not harvested report
jihoojo03/UNet-CBAM_Keras mentioned on GitHubSyntology: not harvested report
kishanAk21/Skin-Cancer-Image-Classification mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified); nothing checks that they implement this paper's method. report
kobiso/CBAM-keras mentioned on GitHubtfMITSyntology: 11 samples, 6 ran (0 instrument-failed) · 5 unverified report
kobiso/CBAM-tensorflow mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
kobiso/CBAM-tensorflow-slim mentioned on GitHubtfMITSyntology: 4 samples, 0 ran · 4 unverified report
laugh12321/3D-Attention-Keras mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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
vinthony/s2am mentioned on GitHubpytorchSyntology: not harvested report
2023-MindSpore-1/ms-code-17 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-6 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code8 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code7 mindsporeSyntology: not harvested report
Jongchan/attention-module pytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
MindSpore-paper-code-3/code6 mindsporeSyntology: not harvested report
MohamedFarag21/DL-papers-implementation tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. report
mindspore-courses/External-Attention-MindSpore mindsporeSyntology: not harvested report
xmu-xiaoma666/External-Attention-pytorch pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), RepVGG: Making VGG-style ConvNets Great Again (arXiv:2101.03697; that paper's own run record: 13 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified), Involution: Inverting the Inherence of Convolution for Visual Recognition (arXiv:2103.06255; that paper's own run record: 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 7 samples that ran constructed an object rather than computing a result) and 4 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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

22 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 9 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
9ran
9unverified

Licence: 3 of the 22 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 6 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. 1 sample whose link to this paper records no repository is 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.

LKLQQ/CBAM community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
get_lr in 91 papers src/get_lr.py ran Apache-2.0 (permissive) · 88b73ea143b80bda · report fixture: signature init_lr:float/0/float, total_epoch:int/0/int, step_per_epoch:int/0/int, anneal_step:int/0/int · returned ndarray · level recorded 2026-09-26
merge in 85 papers src/model_utils/config.py ran · our draft was wrong Apache-2.0 (permissive) · b9e24c3e3e0e88a7 · report fixture: signature args:Namespace/0/?, cfg:dict/0/? · returned dict · level recorded 2026-09-22
parse_cli_to_yaml in 29 papers src/model_utils/config.py ran Apache-2.0 (permissive) · 738456e1b7388e7e · report fixture: signature parser:ArgumentParser/0/?, cfg:dict/0/?, helper:dict/0/?, choices:dict/0/?, cfg_path:str/0/str · returned Namespace · level recorded 2026-09-24
parse_yaml in 32 papers src/model_utils/config.py ran Apache-2.0 (permissive) · 96a9939953d5992d · report fixture: signature yaml_path:str/0/str · returned tuple · level recorded 2026-09-25
kobiso/CBAM-keras community (archive-listed) 11 samples, 6 ran (0 instrument-failed) · 5 unverified
conv2d_bn in 12 papers models/inception_resnet_v2.py ran MIT (permissive) · 83d32f91c543bc87 · report fixture: signature x:KerasTensor/0/float, filters:int/0/int, kernel_size:tuple/1/int, strides:int/0/int, padding:str/0/str, activation:str/0/str, use_bias:bool/0/bool, name:str/0/str · returned KerasTensor · level recorded 2026-09-26
lr_schedule in 30 papers utils.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 67e18e3fdd805d03 · report fixture: signature epoch:int/0/int · returned float · level recorded 2026-09-22
preprocess_input in 26 papers models/inception_resnet_v2.py ran fingerprinted MIT (permissive) · de695392eae44227 · report fixture: signature x:ndarray/4/float · returned ndarray · level recorded 2026-09-25
preprocess_input in 26 papers models/inception_v3.py ran fingerprinted MIT (permissive) · bee766c6e15044c2 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
preprocess_input in 26 papers models/densenet.py ran MIT (permissive) · 2b2390bcd64e4f4f · report fixture: signature x:ndarray/4/float, data_format:str/0/str · returned ndarray · level recorded 2026-09-26
resnet_layer in 10 papers models/resnet_v1.py ran MIT (permissive) · 7c10248ed4cd4926 · report fixture: signature inputs:KerasTensor/0/float, num_filters:int/0/int, kernel_size:int/0/int, strides:int/0/int, activation:str/0/str, batch_normalization:bool/0/bool, conv_first:bool/0/bool · returned KerasTensor · level recorded 2026-09-25
attach_attention_module models/attention_module.py unverified MIT (permissive) · 99ef7bfe54c20e2c · report
cbam_block models/attention_module.py unverified MIT (permissive) · 4b28bc67bccc6824 · report
channel_attention models/.ipynb_checkpoints/attention_module-checkpoint.py unverified MIT (permissive) · 64f4bec6efc96976 · report
relu6 in 14 papers models/mobilenets.py unverified MIT (permissive) here; the stored copy is pointer only · f124399d87a3224b · report
se_block models/attention_module.py unverified MIT (permissive) · 9ae7eb77f5b70d3f · report
kobiso/CBAM-tensorflow community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
parse_arguments in 61 papers Inception_v4.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 · our draft was wrong licence of this copy not recorded · f891cdc1c30186df · report fixture: signature argv:list/1/str · returned Namespace · level recorded 2026-09-22
kobiso/CBAM-tensorflow-slim community (archive-listed) 4 samples, 0 ran · 4 unverified
attach_attention_module nets/attention_module.py unverified MIT (permissive) · 7751ab2f8cae06ed · report
cbam_block nets/attention_module.py unverified MIT (permissive) · 4a744bbc28fbf323 · report
optimize_clones in 5 papers deployment/model_deploy.py unverified MIT (permissive) · 3fe5f08cb1872f05 · report
se_block nets/attention_module.py unverified MIT (permissive) · 0a52a7e8f9cf524b · report
laugh12321/3D-Attention-Keras community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
cbam_block model/CBAM_attention3D.py ran MIT (permissive) · a743d47f31b227e8 · report fixture: signature feature:EagerTensor/5/float, ratio:int/0/int, kernel_size:int/0/int · returned SymbolicTensor · level recorded 2026-09-26
Jongchan/attention-module community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
logsumexp_2d in 14 papers MODELS/cbam.py ran · our draft was wrong fingerprinted MIT (permissive) · 7abfa32a2f1d7424 · report fixture: signature tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-22

Tasks

General ClassificationImage ClassificationObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection DSEC CBAM mAP 26.1 #7 of 12 Archive leaderboard report
Object Detection PKU-DDD17-Car CBAM mAP50 81.9 #8 of 14 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 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockCBAMConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutFaster R-CNNGlobal Average PoolingGrouped ConvolutionKaiming InitializationMax PoolingMobileNetV1Pointwise ConvolutionRPNRandom Horizontal FlipRandom Resized CropReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionRoIPoolSGD with MomentumSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockStep DecayWeight DecayWide Residual BlockWideResNet

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