{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/psanet-point-wise-spatial-attention-network","title":"PSANet: Point-wise Spatial Attention Network for Scene Parsing","arxiv_id":null,"date":"2018-09-01","proceeding":"ECCV 2018 9","authors":["Hengshuang Zhao","Yi Zhang","Shu Liu","Jianping Shi","Chen Change Loy","Dahua Lin","Jiaya Jia"],"abstract":"We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes. In this paper, we propose the point-wise spatial attention network (PSANet) to relax the local neighborhood constraint. Each position on the feature map is connected to all the other ones through a self-adaptively learned attention mask. Moreover, information propagation in bi-direction for scene parsing is enabled. Information at other positions can be collected to help the prediction of the current position and vice versa, information at the current position can be distributed to assist the prediction of other ones. Our proposed approach achieves top performance on various competitive scene parsing datasets, including ADE20K, PASCAL VOC 2012 and Cityscapes, demonstrating its effectiveness and generality.","url_abs":"http://openaccess.thecvf.com/content_ECCV_2018/html/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.html","url_pdf":"http://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"psanet-point-wise-spatial-attention-network","repo_url":"https://github.com/hszhao/PSANet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"psanet-point-wise-spatial-attention-network","repo_url":"https://github.com/hszhao/semseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"psanet-point-wise-spatial-attention-network","repo_url":"https://github.com/justld/PSANet_paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"psanet-point-wise-spatial-attention-network","repo_url":"https://github.com/open-mmlab/mmsegmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"Position"},{"task_slug":"scene-parsing","task_name":"Scene Parsing"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"psanet","method_name":"PSANet"},{"method_slug":"point-wise-spatial-attention","method_name":"Point-wise Spatial Attention"},{"method_slug":"polynomial-rate-decay","method_name":"Polynomial Rate Decay"},{"method_slug":"random-gaussian-blur","method_name":"Random Gaussian Blur"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"syncbn","method_name":"SyncBN"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"psanet","name":"PSANet","full_name":"PSANet"}],"results":[{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"PSANet (ResNet-101)","rank_in_archive_order":206,"of":235,"metrics":{"Validation mIoU":"43.77"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"PSANet (ResNet-101)","rank_in_archive_order":88,"of":95,"metrics":{"mIoU":"43.77"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"PSANet (ResNet-101)","rank_in_archive_order":52,"of":105,"metrics":{"Mean IoU (class)":"80.1%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}