Methods › General › Attention Mechanisms › SPNet
Strip Pooling Network
SPNet
Introduced by Qibin Hou et al. in Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Spatial pooling usually operates on a small region which limits its capability to capture long-range dependencies and focus on distant regions. To overcome this, Hou et al. proposed strip pooling, a novel pooling method capable of encoding long-range context in either horizontal or vertical spatial domains.
Strip pooling has two branches for horizontal and vertical strip pooling. The horizontal strip pooling part first pools the input feature F ∈ℛ^(C ×H ×W) in the horizontal direction: y¹ = GAPʷ (X) Then a 1D convolution with kernel size 3 is applied in y to capture the relationship between different rows and channels. This is repeated W times to make the output yᵥ consistent with the input shape: yₕ = Expand(Conv1D(y¹)) Vertical strip pooling is performed in a similar way. Finally, the outputs of the two branches are fused using element-wise summation to produce the attention map: s = σ(Conv^(1×1)(yᵥ + yₕ)) Y = s X
The strip pooling module (SPM) is further developed in the mixed pooling module (MPM). Both consider spatial and channel relationships to overcome the locality of convolutional neural networks. SPNet achieves state-of-the-art results for several complex semantic segmentation benchmarks.
Papers archive 2025-07-28
5 shown of 5, 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.
-
Swap Path Network for Robust Person Search Pre-training 6 Dec 2024 · 1 repository · arXiv:2412.05433
-
Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network 12 Jul 2022 · 0 repositories · arXiv:2207.05497
-
SPNet: A novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss 19 Feb 2022 · 0 repositories · arXiv:2202.09515
-
SPNet: Multi-Shell Kernel Convolution for Point Cloud Semantic Segmentation 23 Sep 2021 · 0 repositories · arXiv:2109.11610
-
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing 30 Mar 2020 · 2 repositories · arXiv:2003.13328Syntology ran 2 of 11 samples · 9 unverified
Tasks archive 2025-07-28
10 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 |
|---|---|
| Semantic Segmentation | 2 |
| 3D Object Detection | 1 |
| Autonomous Driving | 1 |
| Decoder | 1 |
| Object Detection | 1 |
| Person Search | 1 |
| Retinal Vessel Segmentation | 1 |
| Scene Parsing | 1 |
| Segmentation | 1 |
| object-detection | 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