{"url":"/method/spnet","slug":"spnet","name":"SPNet","full_name":"Strip Pooling Network","full_name_withheld":false,"description_markdown":"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.  \r\n\r\nStrip pooling has two branches for horizontal  and vertical strip pooling. The horizontal strip pooling part first pools the input feature $F \\in \\mathcal{R}^{C \\times H \\times W}$ in the horizontal direction:\r\n\\begin{align}\r\ny^1 = \\text{GAP}^w (X) \r\n\\end{align}\r\nThen 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 $y_v$  consistent with the input shape:\r\n\\begin{align}\r\n    y_h = \\text{Expand}(\\text{Conv1D}(y^1))\r\n\\end{align}\r\nVertical 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:\r\n\\begin{align}\r\ns &= \\sigma(Conv^{1\\times 1}(y_{v} + y_{h}))\r\n\\end{align}\r\n\\begin{align}\r\nY &= s  X\r\n\\end{align}\r\n\r\nThe 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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Strip Pooling: Rethinking Spatial Pooling for Scene Parsing","paper":"/paper/2003-13328","first_author":"Qibin Hou","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/2003-13328"},"source":{"url":"https://arxiv.org/abs/2003.13328v1","title":"Strip Pooling: Rethinking Spatial Pooling for Scene Parsing","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Attention Mechanisms","url":"/methods/category/attention-mechanisms","pwc_aliases":["attention-mechanisms-1"]}],"n_papers_tagged":5,"archive_num_papers":5,"papers_newest_first":[{"paper":"/paper/swap-path-network-for-robust-person-search","title":"Swap Path Network for Robust Person Search Pre-training","date":"2024-12-06","arxiv_id":"2412.05433","n_code_links":1,"syntology":null},{"paper":null,"title":"Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network","date":"2022-07-12","arxiv_id":"2207.05497","n_code_links":0,"syntology":null},{"paper":null,"title":"SPNet: A novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss","date":"2022-02-19","arxiv_id":"2202.09515","n_code_links":0,"syntology":null},{"paper":null,"title":"SPNet: Multi-Shell Kernel Convolution for Point Cloud Semantic Segmentation","date":"2021-09-23","arxiv_id":"2109.11610","n_code_links":0,"syntology":null},{"paper":"/paper/2003-13328","title":"Strip Pooling: Rethinking Spatial Pooling for Scene Parsing","date":"2020-03-30","arxiv_id":"2003.13328","n_code_links":2,"syntology":{"ran":2,"of":11,"unverified":9,"pointer_only":0}}],"papers_shown":5,"tasks":[{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/3d-object-detection","name":"3D Object Detection","papers":1},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/person-search","name":"Person Search","papers":1},{"task":"/task/retinal-vessel-segmentation","name":"Retinal Vessel Segmentation","papers":1},{"task":"/task/scene-parsing","name":"Scene Parsing","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":10,"n_tasks":10,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2022","papers":2},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/spnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}