Methods › General › Attention Mechanisms › scSE

Spatial and Channel SE Blocks

scSE

4 papers tagged archive 2025-07-28

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.

PaperSource

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.

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.

TaskPapers
Segmentation2
Anatomy1
Decoder1
Diagnostic1
Image Classification1
Semantic Segmentation1
Skull Stripping1
image-classification1

Usage over time archive 2025-07-28

Papers per year tagged with scSE: 2018 to 2023, peak 3 3 0 2018: 1 paper 2018 2019: 0 papers 2019 2020: 0 papers 2020 2021: 0 papers 2021 2022: 0 papers 2022 2023: 3 papers 2023
Papers per year the archive tags with this method, by the paper's archive date (4 dated). Bars are counts, not a trend claim.

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

Attention Mechanisms

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