{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T03:24:41Z","timestamp":1771298681024,"version":"3.50.1"},"reference-count":63,"publisher":"World Scientific Pub Co Pte Ltd","issue":"04","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Neur. Syst."],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:p> Since vision transformers excel at establishing global relationships between features, they play an important role in current vision tasks. However, the global attention mechanism restricts the capture of local features, making convolutional assistance necessary. This paper indicates that transformer-based models can attend to local information without using convolutional blocks, similar to convolutional kernels, by employing a special initialization method. Therefore, this paper proposes a novel hybrid multi-scale model called Frequency-Assisted Local Attention Transformer (FALAT). FALAT introduces a Frequency-Assisted Window-based Positional Self-Attention (FWPSA) module that limits the attention distance of query tokens, enabling the capture of local contents in the early stage. The information from value tokens in the frequency domain enhances information diversity during self-attention computation. Additionally, the traditional convolutional method is replaced with a depth-wise separable convolution to downsample in the spatial reduction attention module for long-distance contents in the later stages. Experimental results demonstrate that FALAT-S achieves 83.0% accuracy on IN-1k with an input size of [Formula: see text] using 29.9[Formula: see text]M parameters and 5.6[Formula: see text]G FLOPs. This model outperforms the Next-ViT-S by 0.9[Formula: see text]AP<jats:sup>b<\/jats:sup>\/0.8[Formula: see text]AP<jats:sup>m<\/jats:sup> with Mask-R-CNN [Formula: see text] on COCO and surpasses the recent FastViT-SA36 by 3.1% mIoU with FPN on ADE20k. <\/jats:p>","DOI":"10.1142\/s0129065725500157","type":"journal-article","created":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T09:57:42Z","timestamp":1735898262000},"source":"Crossref","is-referenced-by-count":4,"title":["Frequency-Assisted Local Attention in Lower Layers of Visual Transformers"],"prefix":"10.1142","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5781-0889","authenticated-orcid":false,"given":"Xin","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering and Automation, Northeastern University, Wenhua Road, Shen Yang, Liao Ning, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8670-9046","authenticated-orcid":false,"given":"Zeyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Automation, Northeastern University, Wenhua Road, Shen Yang, Liao Ning, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6984-594X","authenticated-orcid":false,"given":"Shihua","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Automation, Northeastern University, Wenhua Road, Shen Yang, Liao Ning, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8289-4541","authenticated-orcid":false,"given":"Zhaohui","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Automation, Northeastern University, Wenhua Road, Shen Yang, Liao Ning, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5892-3391","authenticated-orcid":false,"given":"Yongchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Automation, Northeastern University, Wenhua Road, Shen Yang, Liao Ning, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9884-2446","authenticated-orcid":false,"given":"Tianzhuang","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Automation, Northeastern University, Wenhua Road, Shen Yang, Liao Ning, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0519-1124","authenticated-orcid":false,"given":"Yulin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Automation, Northeastern University, Wenhua Road, Shen Yang, Liao Ning, P. R. China"}]}],"member":"219","published-online":{"date-parts":[[2025,2,28]]},"reference":[{"key":"S0129065725500157BIB001","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109552"},{"key":"S0129065725500157BIB002","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065723500521"},{"key":"S0129065725500157BIB004","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065723500107"},{"key":"S0129065725500157BIB005","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065723500168"},{"key":"S0129065725500157BIB006","first-page":"12116","volume":"34","author":"Raghu M.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0129065725500157BIB007","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"S0129065725500157BIB008","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"S0129065725500157BIB009","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2024.115283"},{"key":"S0129065725500157BIB010","doi-asserted-by":"publisher","DOI":"10.1007\/s10694-023-01465-w"},{"key":"S0129065725500157BIB011","first-page":"5037","author":"Gulati A.","journal-title":"Interspeech"},{"key":"S0129065725500157BIB014","doi-asserted-by":"publisher","DOI":"10.1159\/000512985"},{"key":"S0129065725500157BIB015","doi-asserted-by":"publisher","DOI":"10.1111\/mice.13219"},{"key":"S0129065725500157BIB016","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065724500369"},{"key":"S0129065725500157BIB017","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065724500576"},{"key":"S0129065725500157BIB018","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065722500599"},{"key":"S0129065725500157BIB019","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-023-02032-0"},{"key":"S0129065725500157BIB020","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12647"},{"key":"S0129065725500157BIB021","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065723500442"},{"key":"S0129065725500157BIB022","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2682102"},{"key":"S0129065725500157BIB023","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04359-7"},{"key":"S0129065725500157BIB024","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-230702"},{"key":"S0129065725500157BIB025","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065723500600"},{"key":"S0129065725500157BIB026","first-page":"4171","volume-title":"Proc. Conf. American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin J.","year":"2019"},{"key":"S0129065725500157BIB027","first-page":"10347","volume-title":"Proc. 38th Int. Conf. Machine Learning","volume":"139","author":"Touvron H.","year":"2021"},{"key":"S0129065725500157BIB028","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268446"},{"key":"S0129065725500157BIB029","first-page":"5785","volume-title":"Proc. IEEE\/CVF Int. Conf. Computer Vision","author":"Vasu P. K. A.","year":"2023"},{"key":"S0129065725500157BIB030","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00557"},{"key":"S0129065725500157BIB031","doi-asserted-by":"publisher","DOI":"10.1111\/mice.13143"},{"key":"S0129065725500157BIB032","first-page":"30392","volume":"34","author":"Xiao T.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0129065725500157BIB033","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20150"},{"issue":"5","key":"S0129065725500157BIB034","first-page":"6575","volume":"45","author":"Yuan L.","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"S0129065725500157BIB035","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"S0129065725500157BIB036","first-page":"6000","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0129065725500157BIB037","first-page":"2286","volume-title":"Proc. 38th Int. Conf. Machine Learning","author":"d\u2019Ascoli S.","year":"2021"},{"key":"S0129065725500157BIB038","doi-asserted-by":"publisher","DOI":"10.1109\/ICBAIE52039.2021.9389905"},{"key":"S0129065725500157BIB039","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"S0129065725500157BIB040","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"S0129065725500157BIB041","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"S0129065725500157BIB042","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"S0129065725500157BIB045","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"S0129065725500157BIB046","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"S0129065725500157BIB047","first-page":"395","volume-title":"Computer Visison \u2014 ECCV 2024","author":"Kim D.","year":"2024"},{"key":"S0129065725500157BIB048","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"S0129065725500157BIB049","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"S0129065725500157BIB050","first-page":"249","volume-title":"Proc. 13th Int. Conf. Artificial Intelligence and Statistics","author":"Glorot X.","year":"2010"},{"key":"S0129065725500157BIB051","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"S0129065725500157BIB052","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"S0129065725500157BIB053","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20099"},{"key":"S0129065725500157BIB054","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"S0129065725500157BIB055","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"S0129065725500157BIB057","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"S0129065725500157BIB058","first-page":"9355","volume":"34","author":"Chu X.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0129065725500157BIB059","first-page":"30008","volume":"34","author":"Yang J.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0129065725500157BIB060","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"S0129065725500157BIB061","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"S0129065725500157BIB064","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"S0129065725500157BIB066","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"S0129065725500157BIB067","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"S0129065725500157BIB068","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"S0129065725500157BIB069","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3202765"},{"key":"S0129065725500157BIB070","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"S0129065725500157BIB071","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3190448"},{"key":"S0129065725500157BIB072","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04146-4"}],"container-title":["International Journal of Neural Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0129065725500157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T09:05:51Z","timestamp":1741251951000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0129065725500157"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,28]]},"references-count":63,"journal-issue":{"issue":"04","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10.1142\/S0129065725500157"],"URL":"https:\/\/doi.org\/10.1142\/s0129065725500157","relation":{},"ISSN":["0129-0657","1793-6462"],"issn-type":[{"value":"0129-0657","type":"print"},{"value":"1793-6462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,28]]},"article-number":"2550015"}}