Methods › General › Attention Mechanisms › scSE
Spatial and Channel SE Blocks
scSE
Introduced by Abhijit Guha Roy et al. in Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
To aggregate global spatial information, an SE block applies global pooling to the feature map. However, it ignores pixel-wise spatial information, which is important in dense prediction tasks. Therefore, Roy et al. proposed spatial and channel SE blocks (scSE). Like BAM, spatial SE blocks are used, complementing SE blocks, to provide spatial attention weights to focus on important regions.
Given the input feature map X, two parallel modules, spatial SE and channel SE, are applied to feature maps to encode spatial and channel information respectively. The channel SE module is an ordinary SE block, while the spatial SE module adopts 1×1 convolution for spatial squeezing. The outputs from the two modules are fused. The overall process can be written as s_c = σ(W₂ δ(W₁GAP(X))) X_(chn) = s_c X sₛ = σ(Conv^(1×1)(X)) Xₛₚₐ = sₛ X Y = f(Xₛₚₐ,X_(chn))
where f denotes the fusion function, which can be maximum, addition, multiplication or concatenation.
The proposed scSE block combines channel and spatial attention to enhance features as well as capturing pixel-wise spatial information. Segmentation tasks are greatly benefited as a result. The integration of an scSE block in F-CNNs makes a consistent improvement in semantic segmentation at negligible extra cost.
Papers archive 2025-07-28
4 shown of 4, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Semi-supervised Learning for Segmentation of Bleeding Regions in Video Capsule Endoscopy 5 Aug 2023 · 0 repositories · arXiv:2308.02869
-
FUSegNet: A Deep Convolutional Neural Network for Foot Ulcer Segmentation 4 May 2023 · 1 repository · arXiv:2305.02961
-
Attention-based convolutional neural network for perfusion T2-weighted MR images preprocessing 4 Mar 2023 · 0 repositories · arXiv:2303.02518
-
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks 23 Aug 2018 · 5 repositories · arXiv:1808.08127Syntology ran 2 of 8 samples · 6 unverified
Tasks archive 2025-07-28
8 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Segmentation | 2 |
| Anatomy | 1 |
| Decoder | 1 |
| Diagnostic | 1 |
| Image Classification | 1 |
| Semantic Segmentation | 1 |
| Skull Stripping | 1 |
| image-classification | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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