{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T19:47:40Z","timestamp":1772567260589,"version":"3.50.1"},"reference-count":59,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"content-version":"vor","delay-in-days":193,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB2007700"],"award-info":[{"award-number":["2020YFB2007700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009002","name":"Shanghai University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:p>Lightweight, high\u2010performance networks are important in vision perception systems. Recent research on convolutional neural networks has shown that attention mechanisms can significantly improve the network performance. However, existing approaches either ignore the significance of using both types of attention mechanisms (channel and space) simultaneously or increase the model complexity. In this study, we propose the adaptive attention module (AAM), which is a truly lightweight yet effective module that comprises channel and spatial submodules to balance model performance and complexity. The AAM initially utilizes the channel submodule to generate intermediate channel\u2010refined features. In this module, an adaptive mechanism enables the model to autonomously learn the weights between features extracted by global max pooling and global average pooling to adapt to different stages of the model, thus enhancing performance. The spatial submodule employs a group\u2010interact\u2010aggregate strategy to enhance the expression of important features. It groups the intermediate channel\u2010refined features along the channel dimension into multiple subfeatures for parallel processing and generates spatial attention feature descriptors and channelwise refined subfeatures for each subfeature; subsequently, it aggregates all the refined subfeatures and employs a \u201cchannel shuffle\u201d operator to transfer information between different subfeatures, thereby generating the final refined features and adaptively emphasizing important regions. Additionally, AAM is a plug\u2010and\u2010play architectural unit that can be directly used to replace standard convolutions in various convolutional neural networks. Extensive tests on CIFAR\u2010100, ImageNet\u20101k, BDD100K, and MS COCO demonstrate that AAM improves the baseline network performance under various models and tasks, thereby validating its versatility.<\/jats:p>","DOI":"10.1155\/2024\/3934270","type":"journal-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T10:35:13Z","timestamp":1720780513000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Adaptive Attention Module for Image Recognition Systems in Autonomous Driving"],"prefix":"10.1155","volume":"2024","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5805-9844","authenticated-orcid":false,"given":"Xianghua","family":"Ma","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7372-1626","authenticated-orcid":false,"given":"Kaitao","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Xiangyu","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Shining","family":"Chen","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2024,7,12]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3189741"},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2022.3218575"},{"key":"e_1_2_9_3_2","doi-asserted-by":"crossref","unstructured":"DongZ. ShiW. TongG. andYangK. Collaborative autonomous driving: vision and challenges Proceedings of the 2020 international conference on connected and autonomous driving (MetroCAD) February 2020 Detroit MI USA IEEE 17\u201326.","DOI":"10.1109\/MetroCAD48866.2020.00010"},{"key":"e_1_2_9_4_2","unstructured":"ToddL. Autonomous vehicle implementation predictions: implications for transport planning 2020 https:\/\/www.vtpi.org\/avip.pdf."},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.enpol.2019.06.013"},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2953675"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2948881"},{"key":"e_1_2_9_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2946967"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2865280"},{"key":"e_1_2_9_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2020.2972974"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3158253"},{"key":"e_1_2_9_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3177210"},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2019.2913883"},{"key":"e_1_2_9_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3190263"},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3207665"},{"key":"e_1_2_9_16_2","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky A.","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_17_2","doi-asserted-by":"crossref","unstructured":"SimonyanK.andZissermanA. Very deep convolutional networks for large-scale image recognition 2015 https:\/\/arxiv.org\/abs\/1409.1556.","DOI":"10.1109\/ICCV.2015.314"},{"key":"e_1_2_9_18_2","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep residual learning for image recognition https:\/\/arxiv.org\/abs\/1512.03385."},{"key":"e_1_2_9_19_2","doi-asserted-by":"crossref","unstructured":"SzegedyC. LiuW. JiaY. SermanetP. ReedS. AnguelovD. andRabinovichA. Going deeper with convolutions Proceedings of the IEEE conference on computer vision and pattern recognition June 2015 Boston MA USA 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_9_20_2","unstructured":"ZagoruykoS.andKomodakisN. Wide residual networks 2016 https:\/\/arxiv.org\/abs\/1605.07146."},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"XieS. GirshickR. Doll\u00e1rP. TuZ. andHeK. Aggregated residual transformations for deep neural networks Proceedings of the IEEE conference on computer vision and pattern recognition July 2017 Honolulu HI USA 1492\u20131500.","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_2_9_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"e_1_2_9_23_2","doi-asserted-by":"crossref","unstructured":"CholletF. Xception: deep learning with depthwise separable convolutions Proceedings of the IEEE conference on computer vision and pattern recognition July 2017 Honolulu HI USA 1251\u20131258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_2_9_24_2","unstructured":"HuJ. ShenL. AlbanieS. SunG. andWuE. Squeeze-and-Excitation networks 2019 https:\/\/arxiv.org\/abs\/1709.01507."},{"key":"e_1_2_9_25_2","unstructured":"ParkJ. WooS. andLeeJ.-Y. BAM: bottleneck attention module 2018 https:\/\/arxiv.org\/abs\/1807.06514."},{"key":"e_1_2_9_26_2","doi-asserted-by":"crossref","unstructured":"WooS. ParkJ. LeeJ.-Y. andKweonI. S. Cbam: convolutional block attention module Computer Vision \u2013 ECCV 2018 Proceedings of the European conference on computer vision (ECCV) October 2018 Tel Aviv Israel 3\u201319 https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1 2-s2.0-85055111544.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_2_9_27_2","unstructured":"YuanY. HuangL. GuoJ. ZhangC. ChenX. andWangJ. Ocnet: object context network for scene parsing 2018 https:\/\/arxiv.org\/abs\/1809.00916."},{"key":"e_1_2_9_28_2","doi-asserted-by":"crossref","unstructured":"CaoY. XuJ. LinS. WeiF. andHuH. Gcnet: non-local networks meet squeeze-excitation networks and beyond Proceedings of the IEEE\/CVF international conference on computer vision workshops October 2019 Montreal BC Canada.","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"e_1_2_9_29_2","doi-asserted-by":"crossref","unstructured":"HuangZ. WangX. HuangL. HuangC. WeiY. andLiuW. Ccnet: criss-cross attention for semantic segmentation Proceedings of the IEEE\/CVF international conference on computer vision October 2019 Montreal BC Canada.","DOI":"10.1109\/ICCV.2019.00069"},{"key":"e_1_2_9_30_2","unstructured":"LiX. HuX. andYangJ. Spatial group-wise enhance: improving semantic feature learning in convolutional networks 2019 https:\/\/arxiv.org\/abs\/1905.09646."},{"key":"e_1_2_9_31_2","doi-asserted-by":"crossref","unstructured":"LiX. WangW. HuX. andYangJ. Selective kernel networks Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 510\u2013519.","DOI":"10.1109\/CVPR.2019.00060"},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"HouQ. ZhouD. andFengJ. Coordinate attention for efficient mobile network design Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition June 2021 Nashville TN USA 13713\u201313722.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"ZhangQ.-L.andYangY.-B. Sa-net: shuffle attention for deep convolutional neural networks Proceedings of the ICASSP 2021-2021 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) June 2021 Toronto ON Canada IEEE 2235\u20132239.","DOI":"10.1109\/ICASSP39728.2021.9414568"},{"key":"e_1_2_9_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108785"},{"key":"e_1_2_9_35_2","doi-asserted-by":"publisher","DOI":"10.3390\/math10101750"},{"key":"e_1_2_9_36_2","doi-asserted-by":"crossref","unstructured":"WangQ. WuB. ZhuP. LiP. ZuoW. andHuQ. ECA-net: efficient channel attention for deep convolutional neural networks 2020 https:\/\/arxiv.org\/abs\/1910.03151.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"e_1_2_9_37_2","doi-asserted-by":"crossref","unstructured":"LiX. WangW. HuX. andYangJ. Selective kernel networks Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition June 2019 Long Beach CA USA 510\u2013519.","DOI":"10.1109\/CVPR.2019.00060"},{"key":"e_1_2_9_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122804"},{"key":"e_1_2_9_39_2","doi-asserted-by":"crossref","unstructured":"ZhangX. ZhouX. LinM. andSunJ. ShuffleNet: an extremely efficient convolutional neural network for mobile devices 2017 https:\/\/arxiv.org\/abs\/1707.01083.","DOI":"10.1109\/CVPR.2018.00716"},{"key":"e_1_2_9_40_2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6663851"},{"key":"e_1_2_9_41_2","unstructured":"HowardA. G. ZhuM. ChenB. KalenichenkoD. WangW. WeyandT. andAdamH. MobileNets: efficient convolutional neural networks for mobile vision applications https:\/\/arxiv.org\/abs\/1704.04861."},{"key":"e_1_2_9_42_2","doi-asserted-by":"crossref","unstructured":"SandlerM. HowardA. ZhuM. ZhmoginovA. andChenL.-C. Mobilenetv2: inverted residuals and linear bottlenecks Proceedings of the IEEE conference on computer vision and pattern recognition June 2018 Salt Lake City UT USA 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_2_9_43_2","doi-asserted-by":"crossref","unstructured":"HowardA. SandlerM. ChuG. ChenL. C. ChenB. TanM. andAdamH. Searching for mobilenetv3 Proceedings of the IEEE\/CVF International Conference on Computer Vision October 2019 Seoul Korea (South) 1314\u20131324.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_2_9_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"e_1_2_9_45_2","doi-asserted-by":"crossref","unstructured":"WangX. GirshickR. GuptaA. andHeK. Non-local neural networks Proceedings of the IEEE conference on computer vision and pattern recognition June 2018 Salt Lake City UT USA 7794\u20137803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_2_9_46_2","doi-asserted-by":"crossref","unstructured":"FuJ. LiuJ. TianH. LiY. BaoY. FangZ. andLuH. Dual attention network for scene segmentation Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition June 2019 Long Beach CA USA 3146\u20133154.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"e_1_2_9_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2021.3093795"},{"key":"e_1_2_9_48_2","doi-asserted-by":"crossref","unstructured":"ZhangQ. JiangZ. andLuQ. Split to be slim: an overlooked redundancy in vanilla convolution 2020 https:\/\/arxiv.org\/abs\/2006.12085.","DOI":"10.24963\/ijcai.2020\/442"},{"key":"e_1_2_9_49_2","unstructured":"ShiD. TransNeXt: robust foveal visual perception for vision transformers 2023 https:\/\/arxiv.org\/abs\/2311.17132."},{"key":"e_1_2_9_50_2","doi-asserted-by":"crossref","unstructured":"GuoX. YangK. andYangW. Group-wise correlation stereo network Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition June 2019 Long Beach CA USA 3273\u20133282.","DOI":"10.1109\/CVPR.2019.00339"},{"key":"e_1_2_9_51_2","first-page":"91","article-title":"Faster r-cnn: towards real-time object detection with region proposal networks","volume":"28","author":"Ren S.","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_52_2","doi-asserted-by":"crossref","unstructured":"HeK. GkioxariG. Doll\u00e1rP. andGirshickR. Mask r-cnn Proceedings of the IEEE international conference on computer vision June 2017 Cambridge MA USA 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_9_53_2","doi-asserted-by":"crossref","unstructured":"LinT.-Y. Doll\u00e1rP. GirshickR. HeK. HariharanB. andBelongieS. Feature pyramid networks for object detection Proceedings of the IEEE conference on computer vision and pattern recognition July 2017 Honolulu HI USA 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_9_54_2","doi-asserted-by":"crossref","unstructured":"KirillovA. GirshickR. HeK. andDoll\u00e1rP. Panoptic feature pyramid networks Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition June 2019 Long Beach CA USA 6399\u20136408.","DOI":"10.1109\/CVPR.2019.00656"},{"key":"e_1_2_9_55_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1339-y"},{"key":"e_1_2_9_56_2","unstructured":"HanC. ZhaoQ. ZhangS. ChenY. ZhangZ. andYuanJ. YOLOPv2: better faster stronger for panoptic driving perception 2022 https:\/\/arxiv.org\/abs\/2208.11434."},{"key":"e_1_2_9_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2021.3062324"},{"key":"e_1_2_9_58_2","doi-asserted-by":"crossref","unstructured":"ChenJ. KaoS. andHeH. Run Don\u2032t walk: chasing higher FLOPS for faster neural networks Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2023 Vancouver BC Canada 12021\u201312031.","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"e_1_2_9_59_2","doi-asserted-by":"crossref","unstructured":"LiJ. WenY. andHeL. Scconv: spatial and channel reconstruction convolution for feature redundancy Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2023 Vancouver BC Canada 6153\u20136162.","DOI":"10.1109\/CVPR52729.2023.00596"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2024\/3934270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T23:59:07Z","timestamp":1732406347000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2024\/3934270"}},"subtitle":[],"editor":[{"given":"Fabio","family":"Caraffini","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":59,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["10.1155\/2024\/3934270"],"URL":"https:\/\/doi.org\/10.1155\/2024\/3934270","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"2023-11-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3934270"}}