{"url":"/method/point-wise-spatial-attention","slug":"point-wise-spatial-attention","name":"Point-wise Spatial Attention","full_name":"Point-wise Spatial Attention","full_name_withheld":false,"description_markdown":"**Point-wise Spatial Attention (PSA)** is a [semantic segmentation](https://paperswithcode.com/task/semantic-segmentation) module. The goal is capture contextual information, especially in the long range, by aggregating information. Through the PSA module, information aggregation is performed as a kind of information flow where we adaptively learn a pixel-wise global attention map for each position from two perspectives to aggregate contextual information over the entire feature map.\r\n\r\nThe PSA module takes a spatial feature map $\\mathbf{X}$ as input. We denote the spatial size of $\\mathbf{X}$ as $H \\times W$. Through the two branches as illustrated, we generate pixel-wise global attention maps for each position in feature map $\\mathbf{X}$ through several convolutional layers.\r\n\r\nWe aggregate input feature maps based on attention maps to generate new feature representations with the long-range contextual information incorporated, i.e., $\\mathbf{Z}\\_{c}$ from the ‘collect’ branch and $\\mathbf{Z}\\_{d}$ from the ‘distribute’ branch.\r\n\r\nWe concatenate the new representations $\\mathbf{Z}\\_{c}$ and $\\mathbf{Z}\\_{d}$ and apply a convolutional layer with [batch normalization](https://paperswithcode.com/method/batch-normalization) and activation layers for dimension reduction and feature fusion. Then we concatenate the new global contextual feature with the local representation feature $\\mathbf{X}$. It is followed by one or several convolutional layers with batch normalization and activation layers to generate the final feature map for following subnetworks.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.html","title":"PSANet: Point-wise Spatial Attention Network for Scene Parsing","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/hszhao/semseg/blob/7192f922b99468969cfd4535e3e35a838994b115/model/psanet.py#L9","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Semantic Segmentation Modules","url":"/methods/category/semantic-segmentation-modules","pwc_aliases":[]}],"n_papers_tagged":3,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/neuraltailor-reconstructing-sewing-pattern","title":"NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments","date":"2022-01-31","arxiv_id":"2201.13063","n_code_links":1,"syntology":{"ran":0,"of":3,"unverified":3,"pointer_only":0}},{"paper":null,"title":"Point Attention Network for Semantic Segmentation of 3D Point Clouds","date":"2019-09-27","arxiv_id":"1909.12663","n_code_links":0,"syntology":null},{"paper":"/paper/psanet-point-wise-spatial-attention-network","title":"PSANet: Point-wise Spatial Attention Network for Scene Parsing","date":"2018-09-01","arxiv_id":null,"n_code_links":4,"syntology":null}],"papers_shown":3,"tasks":[{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/3d-shape-recognition","name":"3D Shape Recognition","papers":1},{"task":"/task/3d-shape-reconstruction","name":"3D Shape Reconstruction","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/point-cloud-segmentation","name":"Point Cloud Segmentation","papers":1},{"task":null,"name":"Position","papers":1},{"task":"/task/scene-parsing","name":"Scene Parsing","papers":1},{"task":"/task/structured-prediction","name":"Structured Prediction","papers":1},{"task":"/task/virtual-try-on","name":"Virtual Try-on","papers":1}],"tasks_shown":10,"n_tasks":10,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":1},{"year":"2022","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/point-wise-spatial-attention"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}