Papers › Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze &...

Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks

23 Aug 2018arXiv:1808.08127archive 2025-07-28

Abhijit Guha Roy, Nassir Navab, Christian Wachinger

In a wide range of semantic segmentation tasks, fully convolutional neural networks (F-CNNs) have been successfully leveraged to achieve state-of-the-art performance. Architectural innovations of F-CNNs have mainly been on improving spatial encoding or network connectivity to aid gradient flow. In this article, we aim towards an alternate direction of recalibrating the learned feature maps adaptively; boosting meaningful features while suppressing weak ones. The recalibration is achieved by simple computational blocks that can be easily integrated in F-CNNs architectures. We draw our inspiration from the recently proposed 'squeeze & excitation' (SE) modules for channel recalibration for image classification. Towards this end, we introduce three variants of SE modules for segmentation, (i) squeezing spatially and exciting channel-wise, (ii) squeezing channel-wise and exciting spatially and (iii) joint spatial and channel 'squeeze & excitation'. We effectively incorporate the proposed SE blocks in three state-of-the-art F-CNNs and demonstrate a consistent improvement of segmentation accuracy on three challenging benchmark datasets. Importantly, SE blocks only lead to a minimal increase in model complexity of about 1.5%, while the Dice score increases by 4-9% in the case of U-Net. Hence, we believe that SE blocks can be an integral part of future F-CNN architectures.

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="1808.08127")

Code

Syntology Ran 2 of 8 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: community (archive-listed): 8 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

abhi4ssj/squeeze_and_excitation mentioned on GitHubpytorchMIT report
ai-med/squeeze_and_excitation mentioned on GitHubpytorchMIT report
highwaywu/tianchi-fft2 mentioned on GitHubpytorch report
ioanvl/1d_squeeze_excitation mentioned 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

8 samples harvested; 2 ran; 0 honoured the contract we drafted; 6 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
6unverified

Licence: 0 of the 8 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 qubvel/segmentation_models.pytorch. “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.

round_filters qubvel/segmentation_models.pytorch/segmentation_models_pytorch/encoders/_efficientnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · f15a49337e69e937 · report
round_repeats qubvel/segmentation_models.pytorch/segmentation_models_pytorch/encoders/_efficientnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · dbc0ca08d119a5a0 · report
adaptive_avgmax_pool2d qubvel/segmentation_models.pytorch/segmentation_models_pytorch/encoders/_dpn.py community (archive-listed) unverified MIT (permissive) · d892754cd88987af · report
drop_connect qubvel/segmentation_models.pytorch/segmentation_models_pytorch/encoders/_efficientnet.py community (archive-listed) unverified MIT (permissive) · 7366397639253b99 · report
from_pretrained qubvel/segmentation_models.pytorch/segmentation_models_pytorch/base/hub_mixin.py community (archive-listed) unverified MIT (permissive) · 9357c02240b5ef34 · report
get_norm_layer qubvel/segmentation_models.pytorch/segmentation_models_pytorch/base/modules.py community (archive-listed) unverified MIT (permissive) · 1c92dfee49c6912e · report
pooling_factor qubvel/segmentation_models.pytorch/segmentation_models_pytorch/encoders/_dpn.py community (archive-listed) unverified MIT (permissive) · 3a8857dbf960f1e4 · report
supports_config_loading qubvel/segmentation_models.pytorch/segmentation_models_pytorch/base/hub_mixin.py community (archive-listed) unverified MIT (permissive) · 13c6bced58eb956a · report

Tasks

Image ClassificationSegmentationSemantic Segmentationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Channel Squeeze and Spatial Excitation, Concurrent Spatial and Channel Squeeze & Excitation, scSE

Average PoolingChannel Squeeze and Spatial ExcitationConcatenated Skip ConnectionConcurrent Spatial and Channel Squeeze & ExcitationConvolutionDense ConnectionsMax PoolingReLUSigmoid ActivationSqueeze-and-Excitation BlockU-NetscSE

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