Papers › Squeeze-and-Excitation Networks

Squeeze-and-Excitation Networks

5 Sep 2017CVPR 2018 6arXiv:1709.01507archive 2025-07-28

Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Enhua Wu

The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy. In this work, we focus instead on the channel relationship and propose a novel architectural unit, which we term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. We further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost. Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2.251%, surpassing the winning entry of 2016 by a relative improvement of ~25%. Models and code are available at https://github.com/hujie-frank/SENet.

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="1709.01507")

Code

Syntology Ran 2 of 9 code samples harvested from 3 repositories linked to this paper; 7 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: community (archive-listed): 7 samples from 3 repositories, 0 ran; 2 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.

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

hujie-frank/SENet officialmentioned in papermentioned on GitHubtf report
AI-Huang/SENet mentioned on GitHubtf report
ArivCR7/Melanoma_Classifier mentioned on GitHubpytorch report
DarshanDeshpande/jax-models mentioned on GitHubjax report
Deci-AI/super-gradients mentioned on GitHubpytorch report
IMvision12/keras-vision-models mentioned on GitHubpytorch report
Knight825/models-pytorch mentioned on GitHubpytorchApache-2.0 report
Legoons/Whale_Classification mentioned on GitHub report
Mayurji/Image-Classification-PyTorch mentioned on GitHubpytorch report
Mind23-2/MindCode-72 mentioned on GitHubmindspore report
RayXie29/SENet_Keras mentioned on GitHub report
Roypic/Attention_Code mentioned on GitHubpytorchMIT report
abhi4ssj/squeeze_and_excitation mentioned on GitHubpytorchMIT report
ahtwq/SENet mentioned on GitHubpytorch report
ai-med/squeeze_and_excitation mentioned on GitHubpytorchMIT report
albanie/collaborative-experts mentioned on GitHubpytorchApache-2.0 report
albanie/mcnSENets mentioned on GitHubpytorch report
alibabasglab/frcrn mentioned on GitHubpytorch report
e96031413/AA-YOLO mentioned on GitHubpytorch report
e96031413/PyTorch_YOLOv4-tiny mentioned on GitHubpytorch report
exekudos/se-resnet mentioned on GitHub report
facebookresearch/ClassyVision mentioned on GitHubpytorch report
fengjiqiang/pretrainedmodel_pytorch mentioned on GitHubpytorch report
harshit0511/Deep-Learning mentioned on GitHubtf report
highwaywu/tianchi-fft2 mentioned on GitHubpytorch report
hikapok/tf-senet mentioned on GitHubtf report
ifrit98/bengaliai mentioned on GitHub report
ioanvl/1d_squeeze_excitation mentioned on GitHubpytorchMIT report
jihoojo03/UNet-CBAM_Keras mentioned on GitHub report
kobiso/CBAM-keras mentioned on GitHubtfMIT report
kobiso/CBAM-tensorflow mentioned on GitHubtf report
kobiso/CBAM-tensorflow-slim mentioned on GitHubtfMIT report
marload/ConvNets-TensorFlow2 mentioned on GitHubtf report
mhorton19/CNN-Kernel-Attention mentioned on GitHubpytorch report
mnikitin/ECANet mentioned on GitHubmxnet report
mnikitin/channel-attention mentioned on GitHubmxnet report
moskomule/senet.pytorch mentioned on GitHubpytorch report
osmr/imgclsmob mentioned on GitHubmxnetMIT report
rishikksh20/ResUnet mentioned on GitHubpytorch report
secretlyvogon/IndRNNTF mentioned on GitHubtfGPL-3.0 report
syiin/human_protein_atlas mentioned on GitHubpytorch report
tensorpack/tensorpack mentioned on GitHubtf report
tsubasawb/DeepLearning_Paper mentioned on GitHub report
varshaneya/Res-SE-Net mentioned on GitHubpytorch report
wolny/pytorch-3dunet mentioned on GitHubpytorch report
yuranusduke/Shift_and_Balance_Attention mentioned on GitHubpytorch report
PaddlePaddle/PaddleClas paddleApache-2.0 report
PaddlePaddle/PaddleOCR paddleApache-2.0 report
open-mmlab/mmpose pytorchApache-2.0 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

9 samples harvested; 2 ran; 0 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.

2ran · our draft was wrong
7unverified

Licence: 6 of the 9 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 3 repositories linked to this paper, official or community; each sample names its own and says which. 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.

cSE piotrplata/squeeze_excitation_keras/csSE.py community (archive-listed) unverified no licence file found · pointer only · 88ae4d609ce773d3 · report
sSE piotrplata/squeeze_excitation_keras/csSE.py community (archive-listed) unverified no licence file found · pointer only · f8055c225dc25839 · report
scSE piotrplata/squeeze_excitation_keras/csSE.py community (archive-listed) unverified no licence file found · pointer only · f3efee3baf1cbc98 · report
se_resnet101 fengjiqiang/pretrainedmodel_pytorch/senet.py community (archive-listed) unverified Apache-2.0 (permissive) · 35bb9d9ac796ead0 · report
se_resnet50 fengjiqiang/pretrainedmodel_pytorch/senet.py community (archive-listed) unverified Apache-2.0 (permissive) · 61ae2ad04883fab3 · report
senet154 fengjiqiang/pretrainedmodel_pytorch/senet.py community (archive-listed) unverified Apache-2.0 (permissive) · 8f8c9882cec4d6a5 · report
validation mhorton19/CNN-Kernel-Attention/dot_product_generated_kernel_cnn.py community (archive-listed) unverified no licence file found · pointer only · c55fc48c6a7bd00e · report
conv3x3 identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 583f9780bdd00a45 · report
parse_arguments identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · f891cdc1c30186df · report

Tasks

Image ClassificationObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 SENet + ShakeShake + Cutout Percentage correct 97.88 #65 of 265 Archive leaderboard report
Image Classification CIFAR-100 SENet + ShakeEven + Cutout Percentage correct 84.59 #75 of 211 Archive leaderboard report
Object Detection DSEC SENet mAP 26.2 #6 of 12 Archive leaderboard report
Object Detection PKU-DDD17-Car SENet mAP50 81.6 #9 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

Introduced by this paper: SENet, Squeeze-and-Excitation Block

Average PoolingConvolutionDense ConnectionsGlobal Average PoolingKaiming InitializationMax PoolingRandom Horizontal FlipRandom Resized CropReLUSENetSGD with MomentumSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockStep Decay

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