{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:05:54Z","timestamp":1753891554316,"version":"3.41.2"},"reference-count":58,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T00:00:00Z","timestamp":1691539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Metric learning, as a fundamental research direction in the field of computer vision, has played a crucial role in image matching. Traditional metric learning methods aim at constructing two-branch siamese neural networks to address the challenge of image matching, but they often overlook to cross-source and cross-view scenarios.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this article, a multi-branch metric learning model is proposed to address these limitations. The main contributions of this work are as follows: Firstly, we design a multi-branch siamese network model that enhances measurement reliability through information compensation among data points. Secondly, we construct a non-local information perception and fusion model, which accurately distinguishes positive and negative samples by fusing information at different scales. Thirdly, we enhance the model by integrating semantic information and establish an information consistency mapping between multiple branches, thereby improving the robustness in cross-source and cross-view scenarios.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Experimental tests which demonstrate the effectiveness of the proposed method are carried out under various conditions, including homologous, heterogeneous, multi-view, and crossview scenarios. Compared to the state-of-the-art comparison algorithms, our proposed algorithm achieves an improvement of ~1, 2, 1, and 1% in terms of similarity measurement Recall@10, respectively, under these four conditions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>In addition, our work provides an idea for improving the crossscene application ability of UAV positioning and navigation algorithm.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnbot.2023.1234129","type":"journal-article","created":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T07:53:31Z","timestamp":1691567611000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Metric networks for enhanced perception of non-local semantic information"],"prefix":"10.3389","volume":"17","author":[{"given":"Jia","family":"Li","sequence":"first","affiliation":[]},{"given":"Yu-qian","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Qiu-yan","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,8,9]]},"reference":[{"key":"B1","first-page":"1578","article-title":"\u201cElasticface: elastic margin loss for deep face recognition,\u201d","author":"Boutros","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B2","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/978-1-0716-0826-5_3","article-title":"Siamese neural networks: an overview","volume":"129","author":"Chicco","year":"2021","journal-title":"Artif. Neural Netw"},{"key":"B3","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10791-007-9039-3","article-title":"Features for image retrieval: an experimental comparison","volume":"11","author":"Deselaers","year":"2008","journal-title":"Inf. Retriev. J"},{"key":"B4","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comp. Vis"},{"key":"B5","first-page":"1060","article-title":"\u201cClothes-changing person re-identification with rgb modality only,\u201d","author":"Gu","year":"","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1703","DOI":"10.1109\/TFUZZ.2022.3214241","article-title":"Multi-objective evolutionary optimisation for prototype-based fuzzy classifiers","volume":"31","author":"Gu","year":"","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"B7","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s41095-022-0271-y","article-title":"Attention mechanisms in computer vision: a survey","volume":"8","author":"Guo","year":"2022","journal-title":"Comp. Vis. Media"},{"key":"B8","first-page":"3279","article-title":"\u201cMatchnet: unifying feature and metric learning for patch-based matching,\u201d","author":"Han","year":"2015","journal-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition"},{"key":"B9","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/j.neucom.2019.11.118","article-title":"A brief survey on semantic segmentation with deep learning","volume":"406","author":"Hao","year":"2020","journal-title":"Neuro Comput"},{"key":"B10","first-page":"4116","article-title":"\u201cContrastive multi-view representation learning on graphs. in international conference on machine learning,\u201d","author":"Hassani","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"B11","article-title":"\u201cDeep residual learning for image recognition,\u201d","author":"He","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B12","first-page":"7132","article-title":"\u201cSqueeze-and-excitation networks,\u201d","author":"Hu","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3231338","article-title":"Causal inference for leveraging image-text matching bias in multi-modal fake news detection","author":"Hu","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B14","doi-asserted-by":"crossref","first-page":"7258","DOI":"10.1109\/CVPR.2018.00758","article-title":"\u201cCvm-net: cross-view matching network for image-based ground-to-aerial geo-localization,\u201d","author":"Hu","year":"2018","journal-title":"2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B15","first-page":"3123","article-title":"\u201cCreating something from nothing: Unsupervised knowledge distillation for cross-modal hashing,\u201d","author":"Hu","year":"2020","journal-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3275644","article-title":"Supervised contrastive learning based on fusion of global and local features for remote sensing image retrieval","volume":"61","author":"Huang","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.3390\/sym11091066","article-title":"Deep metric learning: a survey","volume":"11","author":"Kaya","year":"2019","journal-title":"Symmetry"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3390\/app10175729","article-title":"Enhancing u-net with spatial-channel attention gate for abnormal tissue segmentation in medical imaging","author":"Khanh","year":"2020","journal-title":"Appl. Sci"},{"key":"B19","first-page":"7440","article-title":"\u201cPoint cloud oversegmentation with graph-structured deep metric learning,\u201d","author":"Landrieu","year":"2019","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B20","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B21","doi-asserted-by":"publisher","first-page":"168511","DOI":"10.1109\/ACCESS.2021.3091810","article-title":"A multi-branch feature fusion network for building detection in remote sensing images","volume":"9","author":"Li","year":"2021","journal-title":"IEEE Access"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.104669","article-title":"A comprehensive survey on 3d face recognition methods","author":"Li","year":"2022","journal-title":"Eng. Appl. Artif. Intell"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2021.101513","article-title":"Maximum margin riemannian manifold-based hyperdisk for fault diagnosis of roller bearing with multi-channel fusion covariance matrix","author":"Li","year":"2022","journal-title":"Adv. Eng. Informat"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2022.3151337","article-title":"Locate where you are by block joint learning network","volume":"19","author":"Liu","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2984703","article-title":"Siamese network-based multi-scale deep feature learning for remote sensing image retrieval","author":"Liu","year":"2020","journal-title":"Remote Sensing"},{"key":"B26","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1109\/TMECH.2022.3210592","article-title":"A control strategy of robot eye-head coordinated gaze behavior achieved for minimized neural transmission noise","volume":"28","author":"Liu","year":"2023","journal-title":"IEEE-ASME Transact. Mechatron"},{"key":"B27","doi-asserted-by":"publisher","first-page":"2729","DOI":"10.3390\/s18082729","article-title":"Analysis and modeling methodologies for heat exchanges of deep-sea in situ spectroscopy detection system based on rov","volume":"18","author":"Liu","year":"2018","journal-title":"Nat. Rev. Cancer"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110040","article-title":"Egnn: Graph structure learning based on evolutionary computation helps more in graph neural networks","author":"Liu","year":"2023","journal-title":"Appl. Soft Comput"},{"key":"B29","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s11263-020-01359-2","article-title":"Mage matching from handcrafted to deep features: a survey","volume":"129","author":"Ma","year":"2021","journal-title":"Int. J. Comput. Vis"},{"key":"B30","first-page":"253","article-title":"\u201cSolar: second-order loss and attention for image retrieval,\u201d","author":"Ng","year":"2020","journal-title":"Computer Vision\u2013ECCV 2020: 16th European Conference"},{"key":"B31","doi-asserted-by":"publisher","first-page":"2026","DOI":"10.3390\/math10122026","article-title":"Kernel matrix-based heuristic multiple kernel learning","volume":"10","author":"Price","year":"2022","journal-title":"Mathematics"},{"key":"B32","doi-asserted-by":"publisher","first-page":"4187","DOI":"10.1007\/s10586-018-1731-0","article-title":"Content based image retrieval using deep learning process","volume":"22","author":"Saritha","year":"2019","journal-title":"Cluster Comput"},{"key":"B33","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1109\/CVPR.2015.7298682","article-title":"\u201cFacenet: a unified embedding for face recognition and clustering,\u201d","author":"Schroff","year":"2015","journal-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1109\/TIP.2023.3238642","article-title":"Git: Graph interactive transformer for vehicle re-identification","volume":"32","author":"Shen","year":"2023","journal-title":"IEEE Transact. Image Process"},{"key":"B35","doi-asserted-by":"publisher","first-page":"108339","DOI":"10.1016\/j.nanoen.2023.108339","article-title":"Self-powered difunctional sensors based on sliding contact-electrification and tribovoltaic effects for pneumatic monitoring and controlling","volume":"110","author":"Shi","year":"","journal-title":"Nano Energy"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2022.110001","article-title":"Center-based transfer feature learning with classifier adaptation for surface defect recognition","author":"Shi","year":"","journal-title":"Mech. Syst. Signal Process"},{"key":"B37","doi-asserted-by":"publisher","first-page":"11990","DOI":"10.1609\/aaai.v34i07.6875","article-title":"Optimal feature transport for cross-view image geo-localization","volume":"34","author":"Shi","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B38","doi-asserted-by":"publisher","first-page":"12404","DOI":"10.3934\/mbe.2023552","article-title":"Arc fault detection using artificial intelligence: challenges and benefits","volume":"20","author":"Tian","year":"2023","journal-title":"Math. Biosci. Eng"},{"key":"B39","first-page":"11016","article-title":"\u201cSosnet: second order similarity regularization for local descriptor learning,\u201d","author":"Tian","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B40","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2015.7298790","article-title":"\u201c24\/7 place recognition by view synthesis,\u201d","author":"Torii","year":"2015","journal-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B41","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1109\/TCSVT.2020.2980853","article-title":"Edge-guided non-local fully convolutional network for salient object detection","volume":"31","author":"Tu","year":"2020","journal-title":"IEEE Transact. Circ. Syst. Video Technol"},{"key":"B42","doi-asserted-by":"publisher","first-page":"10495","DOI":"10.3934\/math.2022585","article-title":"An intelligent recognition framework of access control system with anti-spoofing function","volume":"7","author":"Wang","year":"2022","journal-title":"AIMS Math"},{"key":"B43","doi-asserted-by":"crossref","first-page":"2495","DOI":"10.1109\/CVPR46437.2021.00252","article-title":"\u201cUnderstanding the behaviour of contrastive loss,\u201d","author":"Wang","year":"2021","journal-title":"2021IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.05296","article-title":"Learning cross-view geo-localization embeddings via dynamic weighted decorrelation regularization","author":"Wang","year":"2022","journal-title":"arXiv"},{"key":"B45","doi-asserted-by":"publisher","first-page":"867","DOI":"10.1109\/TCSVT.2021.3061265","article-title":"Each part matters: local patterns facilitate cross-view geo-localization","volume":"32","author":"Wang","year":"2021","journal-title":"IEEE Transact. Circ. Syst. Video Technol"},{"key":"B46","doi-asserted-by":"publisher","first-page":"890","DOI":"10.1109\/TCSS.2022.3164719","article-title":"Heterogeneous network representation learning approach for ethereum identity identification","volume":"10","author":"Wang","year":"2023","journal-title":"IEEE Transact. Comp. Soc. Syst"},{"key":"B47","first-page":"3","article-title":"\u201cCbam: convolutional block attention module,\u201d","author":"Woo","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"B48","first-page":"1","article-title":"\u201cWide-area image geolocalization with aerial reference imagery,\u201d","author":"Workman","year":"2015","journal-title":"IEEE International Conference on Computer Vision (ICCV)"},{"key":"B49","doi-asserted-by":"publisher","first-page":"3965","DOI":"10.1109\/TGRS.2017.2685945","article-title":"Aid: A benchmark data set for performance evaluation of aerial scene classification","volume":"55","author":"Xia","year":"2017","journal-title":"IEEE Transact. Geosci. Remote Sensing"},{"key":"B50","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1007\/s11280-018-0541-x","article-title":"Deep adversarial metric learning for cross-modal retrieval","volume":"22","author":"Xu","year":"2019","journal-title":"World Wide Web"},{"key":"B51","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1007\/s40747-022-00841-3","article-title":"A nove1 dual-modal emotion recognition a1gorithm with fusing hybrid features of audio signa1 and speech context","volume":"9","author":"Xu","year":"2023","journal-title":"Comp. Intell. Syst"},{"key":"B52","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1109\/TPAMI.2020.2975798","article-title":"Deep multi-view enhancement hashing for image retrieval","volume":"43","author":"Yan","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JPHOT.2022.3144227","article-title":"Lpso: multi-source image matching considering the description of local phase sharpness orientation","volume":"14","author":"Yang","year":"2022","journal-title":"IEEE Photon. J"},{"key":"B54","first-page":"867","article-title":"\u201cPredicting ground-level scene layout from aerial imagery,\u201d","author":"Zhai","year":"2017","journal-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B55","doi-asserted-by":"publisher","first-page":"1814","DOI":"10.1109\/JSTARS.2022.3148139","article-title":"Progress and challenges in intelligent remote sensing satellite systems","volume":"15","author":"Zhang","year":"2022","journal-title":"IEEE J. Select. Top. Appl. Earth Observ. Remote Sensing"},{"key":"B56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3383184","article-title":"Dual-path convolutional image-text embeddings with instance loss","volume":"16","author":"Zheng","year":"","journal-title":"ACM Transact. Multim. Comp. Commun. Appl"},{"key":"B57","first-page":"1395","article-title":"\u201cUniversity-1652: a multi-view multi-source benchmark for drone-based geo-localization,\u201d","author":"Zheng","year":"","journal-title":"Proceedings of the 28th ACM International Conference on Multimedia"},{"key":"B58","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.isprsjprs.2018.01.004","article-title":"Patternnet: a benchmark dataset for performance evaluation of remote sensing image retrieval","volume":"145","author":"Zhou","year":"2018","journal-title":"ISPRS J. Photogramm. Remote Sensing"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1234129\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T07:53:50Z","timestamp":1691567630000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1234129\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,9]]},"references-count":58,"alternative-id":["10.3389\/fnbot.2023.1234129"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2023.1234129","relation":{},"ISSN":["1662-5218"],"issn-type":[{"type":"electronic","value":"1662-5218"}],"subject":[],"published":{"date-parts":[[2023,8,9]]},"article-number":"1234129"}}