{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T18:15:59Z","timestamp":1789496159192,"version":"build-2803163510"},"reference-count":30,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Innovation Capability Support Program of Shaanxi","award":["2025PT-022"],"award-info":[{"award-number":["2025PT-022"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Attention mechanisms improve convolutional neural networks (CNNs) by emphasizing informative features, but many existing modules introduce additional parameters, convolutional or fully connected layers, and non-negligible computational overhead. These costs may limit their use in lightweight or plug-and-play CNN architectures. To address this issue, this paper proposes a parameter-free spatial attention fusion module (PSAFM). Specifically, the pointwise average- and max-pooling branches are combined by deterministic weighted fusion, after which channel statistics and a Tanh activation are used to compute adaptive three-dimensional attention weights. This enables the module to strengthen feature responses without adding trainable parameters. We evaluate PSAFM on CIFAR-10 and CIFAR-100 using ResNet, Pre-ResNet, and MobileNetV2 backbones. On CIFAR-10, PSAFM achieves the best accuracy in 8 of 9 tested backbone settings and improves the original backbones by 0.32 to 1.81 percentage points. On CIFAR-100, PSAFM achieves the best accuracy in 6 of 9 settings and improves the original backbones by 0.05 to 1.68 percentage points. In these experiments, PSAFM is compared with representative attention modules. The results show that its parameter count remains essentially unchanged and that only a small FLOPs overhead is introduced. In other words, when model compactness is important, PSAFM is a simple and efficient attention module that improves CNN feature representation.<\/jats:p>","DOI":"10.1371\/journal.pone.0357958","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T17:56:08Z","timestamp":1789494968000},"page":"e0357958","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["PSAFM: A parameter-free spatial attention fusion module"],"prefix":"10.1371","volume":"21","author":[{"given":"Guangjun","family":"Liu","sequence":"first","affiliation":[{"name":"School of Ecological Environment and Chemical Engineering, Xi\u2019an University of Technology","place":["Xi\u2019an, P. R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoping","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Mathematics, Xi\u2019an University of Technology","place":["Xi\u2019an, P. R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingkun","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Mathematics, Xi\u2019an University of Technology","place":["Xi\u2019an, P. R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Xi\u2019an Jiaotong University","place":["Xi\u2019an, P. R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yike","family":"Li","sequence":"additional","affiliation":[{"name":"Xijing Hospital of Air Force Military Medical University","place":["Xi\u2019an, P. R. China"],"department":["Department of Thyroid and Breast Surgery"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"pone.0357958.ref001","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, 2012. 1097\u2013105. https:\/\/proceedings.neurips.cc\/paper\/2012\/hash\/c399862d3b9d6b76c8436e924a68c45b-Abstract.html"},{"key":"pone.0357958.ref002","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: 2015. https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"pone.0357958.ref003","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 770\u20138. http:\/\/dx.doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"pone.0357958.ref004","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Y Bengio","year":"1994","journal-title":"IEEE Trans Neural Netw"},{"key":"pone.0357958.ref005","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely Connected Convolutional Networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. 2261\u20139. https:\/\/doi.org\/10.1109\/cvpr.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"pone.0357958.ref006","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv. 2017. https:\/\/doi.org\/1704.04861"},{"key":"pone.0357958.ref007","unstructured":"Tan M, Le Q. EfficientNet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th International Conference on Machine Learning, 2019. 6105\u201314. https:\/\/proceedings.mlr.press\/v97\/tan19a.html"},{"key":"pone.0357958.ref008","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-Excitation Networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018. 7132\u201341. https:\/\/doi.org\/10.1109\/cvpr.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"pone.0357958.ref009","first-page":"3","article-title":"CBAM: Convolutional block attention module. In:","volume-title":"Computer Vision \u2013 ECCV 2018 of Lecture Notes in Computer Science","author":"S Woo","year":"2018"},{"key":"pone.0357958.ref010","doi-asserted-by":"crossref","unstructured":"Hou Q, Zhou D, Feng J. Coordinate Attention for Efficient Mobile Network Design. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. 13708\u201317. https:\/\/doi.org\/10.1109\/cvpr46437.2021.01350","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"pone.0357958.ref011","unstructured":"Yang L, Zhang RY, Li L, Xie X. SimAM: A simple, parameter-free attention module for convolutional neural networks. In: Proceedings of the 38th International Conference on Machine Learning, 2021. 11863\u201374. https:\/\/proceedings.mlr.press\/v139\/yang21o.html"},{"issue":"3","key":"pone.0357958.ref012","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s41095-022-0271-y","article-title":"Attention mechanisms in computer vision: A survey","volume":"8","author":"M-H Guo","year":"2022","journal-title":"Comp Visual Med"},{"issue":"4","key":"pone.0357958.ref013","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1007\/s41095-023-0364-2","article-title":"Visual attention network","volume":"9","author":"M-H Guo","year":"2023","journal-title":"Comp Visual Med"},{"key":"pone.0357958.ref014","doi-asserted-by":"crossref","unstructured":"Ouyang D, He S, Zhang G, Luo M, Guo H, Zhan J, et al. Efficient Multi-Scale Attention Module with Cross-Spatial Learning. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023. 1\u20135. https:\/\/doi.org\/10.1109\/icassp49357.2023.10096516","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"key":"pone.0357958.ref015","doi-asserted-by":"crossref","unstructured":"Li J, Wen Y, He L. SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. 6153\u201362. https:\/\/doi.org\/10.1109\/cvpr52729.2023.00596","DOI":"10.1109\/CVPR52729.2023.00596"},{"key":"pone.0357958.ref016","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","article-title":"Identity mappings in deep residual networks","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016"},{"key":"pone.0357958.ref017","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Komodakis N. Wide Residual Networks. In: Procedings of the British Machine Vision Conference 2016, 2016. 87.1-87.12. https:\/\/doi.org\/10.5244\/c.30.87","DOI":"10.5244\/C.30.87"},{"key":"pone.0357958.ref018","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C. MobileNetV2: Inverted Residuals and Linear Bottlenecks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018. 4510\u201320. https:\/\/doi.org\/10.1109\/cvpr.2018.00474","DOI":"10.1109\/CVPR.2018.00474"},{"key":"pone.0357958.ref019","doi-asserted-by":"crossref","unstructured":"Wang Q, Wu B, Zhu P, Li P, Zuo W, Hu Q. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. 11531\u20139. https:\/\/doi.org\/10.1109\/cvpr42600.2020.01155","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"pone.0357958.ref020","doi-asserted-by":"crossref","first-page":"108785","DOI":"10.1016\/j.patcog.2022.108785","article-title":"HAM: Hybrid attention module in deep convolutional neural networks for image classification","volume":"129","author":"G Li","year":"2022","journal-title":"Pattern Recognition"},{"key":"pone.0357958.ref021","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. In: Advances in Neural Information Processing Systems, 2017. 5998\u20136008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"pone.0357958.ref022","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K. Non-local Neural Networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018. 7794\u2013803. https:\/\/doi.org\/10.1109\/cvpr.2018.00813","DOI":"10.1109\/CVPR.2018.00813"},{"key":"pone.0357958.ref023","doi-asserted-by":"crossref","unstructured":"Cao Y, Xu J, Lin S, Wei F, Hu H. GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), 2019. 1971\u201380. https:\/\/doi.org\/10.1109\/iccvw.2019.00246","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"pone.0357958.ref024","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, et al. Dual Attention Network for Scene Segmentation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. 3141\u20139. https:\/\/doi.org\/10.1109\/cvpr.2019.00326","DOI":"10.1109\/CVPR.2019.00326"},{"key":"pone.0357958.ref025","unstructured":"Xu W, Wan Y. ELA: Efficient local attention for deep convolutional neural networks. 2024. https:\/\/arxiv.org\/abs\/2403.01123"},{"key":"pone.0357958.ref026","volume-title":"Learning multiple layers of features from tiny images","author":"A Krizhevsky","year":"2009"},{"key":"pone.0357958.ref027","unstructured":"Lee CY, Xie S, Gallagher P, Zhang Z, Tu Z. In: Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, 2015. 562\u201370. https:\/\/proceedings.mlr.press\/v38\/lee15a.html"},{"key":"pone.0357958.ref028","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Dollar P, Tu Z, He K. Aggregated Residual Transformations for Deep Neural Networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. 5987\u201395. https:\/\/doi.org\/10.1109\/cvpr.2017.634","DOI":"10.1109\/CVPR.2017.634"},{"key":"pone.0357958.ref029","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, et al. In: Advances in Neural Information Processing Systems, 2019. 8026\u201337. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/bdbca288fee7f92f2bfa9f7012727740-Abstract.html"},{"issue":"9","key":"pone.0357958.ref030","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0307684","article-title":"Enhancing grid reliability through advanced insulator defect identification","volume":"19","author":"X Wang","year":"2024","journal-title":"PLoS One"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T17:56:19Z","timestamp":1789494979000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357958"}},"subtitle":[],"editor":[{"given":"Peng","family":"Geng","sequence":"first","affiliation":[{"name":"Shijiazhuang Tiedao University","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"references-count":30,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0357958","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]}}}