{"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/squeeze-and-attention-networks-for-semantic","title":"Squeeze-and-Attention Networks for Semantic Segmentation","arxiv_id":"1909.03402","date":"2019-09-08","proceeding":"CVPR 2020 6","authors":["Zilong Zhong","Zhong Qiu Lin","Rene Bidart","Xiaodan Hu","Ibrahim Ben Daya","Zhifeng Li","Wei-Shi Zheng","Jonathan Li","Alexander Wong"],"abstract":"The recent integration of attention mechanisms into segmentation networks improves their representational capabilities through a great emphasis on more informative features. However, these attention mechanisms ignore an implicit sub-task of semantic segmentation and are constrained by the grid structure of convolution kernels. In this paper, we propose a novel squeeze-and-attention network (SANet) architecture that leverages an effective squeeze-and-attention (SA) module to account for two distinctive characteristics of segmentation: i) pixel-group attention, and ii) pixel-wise prediction. Specifically, the proposed SA modules impose pixel-group attention on conventional convolution by introducing an 'attention' convolutional channel, thus taking into account spatial-channel inter-dependencies in an efficient manner. The final segmentation results are produced by merging outputs from four hierarchical stages of a SANet to integrate multi-scale contexts for obtaining an enhanced pixel-wise prediction. Empirical experiments on two challenging public datasets validate the effectiveness of the proposed SANets, which achieves 83.2% mIoU (without COCO pre-training) on PASCAL VOC and a state-of-the-art mIoU of 54.4% on PASCAL Context.","url_abs":"https://arxiv.org/abs/1909.03402v4","url_pdf":"https://arxiv.org/pdf/1909.03402v4.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":"squeeze-and-attention-networks-for-semantic","repo_url":"https://github.com/its-mayank/SqueezeAttention-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"squeeze-and-attention-networks-for-semantic","repo_url":"https://github.com/MindCode-4/code-13/tree/main/squeeze-and-attention-networks-for-semantic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"squeeze-and-attention-networks-for-semantic","repo_url":"https://github.com/MindCode-4/code-9/tree/main/squeeze-and-attention-networks-for-semantic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"squeeze-and-attention-networks-for-semantic","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/3/squeeze-and-attention-networks-for-semantic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"SANet (pretraining on COCO dataset)","rank_in_archive_order":6,"of":51,"metrics":{"Mean IoU":"86.1%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"SANet","rank_in_archive_order":19,"of":51,"metrics":{"Mean IoU":"83.2%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.03402","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}