Methods › General › Attention Modules › Spatial Attention-Guided Mask
Spatial Attention-Guided Mask
Introduced by Youngwan Lee et al. in CenterMask : Real-Time Anchor-Free Instance Segmentation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Spatial Attention-Guided Mask is a module for instance segmentation that predicts a segmentation mask on each detected box with a spatial attention map that helps to focus on informative pixels and suppress noise. The goal is to guide the mask head for spotlighting meaningful pixels and repressing uninformative ones.
Once features inside the predicted RoIs are extracted by RoIAlign with 14×14 resolution, those features are fed into four conv layers and the spatial attention module (SAM) sequentially. To exploit the spatial attention map A_(sag)(Xᵢ) ∈ℛ^(1×W×H) as a feature descriptor given input feature map Xᵢ ∈ℛ^(C×W×H), the SAM first generates pooled features P_(avg), Pₘₐₓ ∈ℛ^(1×W×H) by both average and max pooling operations respectively along the channel axis and aggregates them via concatenation. Then it is followed by a 3 × 3 conv layer and normalized by the sigmoid function. The computation process is summarized as follow:
A_(sag)(Xᵢ) = σ(F_(3×3)(Pₘₐₓ ·P_(avg)))
where σ denotes the sigmoid function, F_(3×3) is 3 × 3 conv layer and · represents the concatenate operation. Finally, the attention guided feature map X_(sag) ∈ ℛ^(C×W×H) is computed as:
X_(sag) = A_(sag)(Xᵢ) ⊗Xᵢ
where ⊗ denotes element-wise multiplication. After then, a 2 × 2 deconv upsamples the spatially attended feature map to 28 × 28 resolution. Lastly, a 1 × 1 conv is applied for predicting class-specific masks.
Papers archive 2025-07-28
7 shown of 7, 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.
-
Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding 7 Nov 2022 · 0 repositories · arXiv:2211.03850
-
Intelligent detect for substation insulator defects based on CenterMask 31 Aug 2022 · 0 repositories · arXiv:2208.14598
-
CenterMask: single shot instance segmentation with point representation 9 Apr 2020 · 0 repositories · arXiv:2004.04446
-
SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation 7 Apr 2020 · 4 repositories · arXiv:2004.03696
-
Learning Oracle Attention for High-fidelity Face Completion 31 Mar 2020 · 0 repositories · arXiv:2003.13903
-
Context-Aware Domain Adaptation in Semantic Segmentation 9 Mar 2020 · 0 repositories · arXiv:2003.04010
-
CenterMask : Real-Time Anchor-Free Instance Segmentation 15 Nov 2019 · 8 repositories · arXiv:1911.06667Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
Tasks archive 2025-07-28
17 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
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