{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T13:31:47Z","timestamp":1763904707172},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T00:00:00Z","timestamp":1707091200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T00:00:00Z","timestamp":1707091200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Natural Science Foundation of Shandong Province, China","award":["ZR2019MF073","ZR2019MF073","ZR2019MF073"],"award-info":[{"award-number":["ZR2019MF073","ZR2019MF073","ZR2019MF073"]}]},{"name":"Fundamental Research Funds for the Central Universities, China University of Petroleum","award":["20CX05001A","20CX05001A","20CX05001A"],"award-info":[{"award-number":["20CX05001A","20CX05001A","20CX05001A"]}]},{"name":"Major Scientific and Technological Projects of CNPC","award":["ZD2019-183-008","ZD2019-183-008","ZD2019-183-008"],"award-info":[{"award-number":["ZD2019-183-008","ZD2019-183-008","ZD2019-183-008"]}]},{"name":"Creative Research Team of Young Scholars at Universities in Shandong Province","award":["2019KJN019","2019KJN019","2019KJN019"],"award-info":[{"award-number":["2019KJN019","2019KJN019","2019KJN019"]}]},{"name":"State Key Laboratory of Shale Oil and Gas Enrichment Mechanisms and Effective Development","award":["33550000-22-ZC0613-0243","33550000-22-ZC0613-0243","33550000-22-ZC0613-0243"],"award-info":[{"award-number":["33550000-22-ZC0613-0243","33550000-22-ZC0613-0243","33550000-22-ZC0613-0243"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The study of few-shot remote sensing image classification has received significant attention. Although meta-learning-based algorithms have been the primary focus of recent examination, feature fusion methods stress feature extraction and representation. Nonetheless, current feature fusion methods, like the multi-head mechanism, are restricted by their complicated network structure and challenging training process. This manuscript presents a simplified multi-head mechanism for obtaining multiple feature representations from a single sample. Furthermore, we perform specific fundamental transformations on remote-sensing images to obtain more suitable features for information representation. Specifically, we reduce multiple feature extractors of the multi-head mechanism to a single one and add an image transformation module before the feature extractor. After transforming the image, the features are extracted resulting in multiple features for each sample. The feature fusion stage is integrated with the classification prediction stage, and multiple linear classifiers are combined for multi-decision fusion to complete feature fusion and classification. By combining image transformation with feature decision fusion, we compare our results with other methods through validation tests and demonstrate that our algorithm simplifies the multi-head mechanism while maintaining or improving classification performance.\n<\/jats:p>","DOI":"10.1007\/s11063-024-11451-0","type":"journal-article","created":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T13:02:21Z","timestamp":1707138141000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Simplified Multi-head Mechanism for Few-Shot Remote Sensing Image Classification"],"prefix":"10.1007","volume":"56","author":[{"given":"Xujian","family":"Qiao","sequence":"first","affiliation":[]},{"given":"Lei","family":"Xing","sequence":"additional","affiliation":[]},{"given":"Anxun","family":"Han","sequence":"additional","affiliation":[]},{"given":"Weifeng","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Baodi","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,2,5]]},"reference":[{"issue":"5","key":"11451_CR1","doi-asserted-by":"publisher","first-page":"2811","DOI":"10.1109\/TGRS.2017.2783902","volume":"56","author":"G Cheng","year":"2018","unstructured":"Cheng G, Yang C, Yao X, Guo L, Han J (2018) When deep learning meets metric learning: remote sensing image scene classification via learning discriminative CNNs. IEEE Trans Geosci Remote Sens 56(5):2811\u20132821","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"11451_CR2","doi-asserted-by":"crossref","unstructured":"Chen Z, Maji S, Learned-Miller E (2021) Shot in the dark: few-shot learning with no base-class labels. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2668\u20132677","DOI":"10.1109\/CVPRW53098.2021.00300"},{"key":"11451_CR3","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning. PMLR, pp 1126\u20131135"},{"key":"11451_CR4","doi-asserted-by":"crossref","unstructured":"Han A, Xing L, Liu W, Liu B (2022) Mvff: multi-view feature fusion for few-shot remote sensing image scene classification. In: 2022 IEEE international conference on systems, man, and cybernetics (SMC). IEEE, pp 2452\u20132458","DOI":"10.1109\/SMC53654.2022.9945314"},{"issue":"21","key":"11451_CR5","doi-asserted-by":"publisher","first-page":"5550","DOI":"10.3390\/rs14215550","volume":"14","author":"N Jiang","year":"2022","unstructured":"Jiang N, Shi H, Geng J (2022) Multi-scale graph-based feature fusion for few-shot remote sensing image scene classification. Remote Sens 14(21):5550","journal-title":"Remote Sens"},{"issue":"13","key":"11451_CR6","doi-asserted-by":"publisher","first-page":"2532","DOI":"10.3390\/rs13132532","volume":"13","author":"J Kim","year":"2021","unstructured":"Kim J, Chi M (2021) Saffnet: self-attention-based feature fusion network for remote sensing few-shot scene classification. Remote Sens 13(13):2532","journal-title":"Remote Sens"},{"key":"11451_CR7","doi-asserted-by":"crossref","unstructured":"Lee K, Maji S, Ravichandran A, Soatto S (2019) Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10657\u201310665","DOI":"10.1109\/CVPR.2019.01091"},{"key":"11451_CR8","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.isprsjprs.2021.08.001","volume":"179","author":"Y Li","year":"2021","unstructured":"Li Y, Kong D, Zhang Y, Tan Y, Chen L (2021) Robust deep alignment network with remote sensing knowledge graph for zero-shot and generalized zero-shot remote sensing image scene classification. ISPRS J Photogram Remote Sens 179:145\u2013158","journal-title":"ISPRS J Photogram Remote Sens"},{"issue":"12","key":"11451_CR9","doi-asserted-by":"publisher","first-page":"10590","DOI":"10.1109\/TGRS.2020.3047447","volume":"59","author":"Y Li","year":"2021","unstructured":"Li Y, Zhu Z, Yu JG, Zhang Y (2021) Learning deep cross-modal embedding networks for zero-shot remote sensing image scene classification. IEEE Trans Geosci Remote Sens 59(12):10590\u201310603","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"11451_CR10","doi-asserted-by":"crossref","unstructured":"Liu D, Bai L, Yu T (2023) Generalized few-shot classification with knowledge graph. Neural Process Lett 1\u201318","DOI":"10.1007\/s11063-023-11278-1"},{"key":"11451_CR11","unstructured":"Liu Y, Lee J, Park M, Kim S, Yang E, Hwang SJ, Yang Y (2018) Learning to propagate labels: Transductive propagation network for few-shot learning. arXiv preprint arXiv:1805.10002"},{"key":"11451_CR12","first-page":"1","volume":"19","author":"H Lv","year":"2022","unstructured":"Lv H, Qian W, Chen T, Yang H, Zhou X (2022) Multiscale feature adaptive fusion for object detection in optical remote sensing images. IEEE Geosci Remote Sens Lett 19:1\u20135","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"11451_CR13","unstructured":"Oreshkin Boris, L\u00f3pez Pau Rodr\u00edguez, Lacoste Alexandre (2018) Tadam: task dependent adaptive metric for improved few-shot learning. Adv Neural Inf Process Syst 31"},{"key":"11451_CR14","doi-asserted-by":"crossref","unstructured":"Shao S, Xing L, Wang Y, Xu R, Zhao C, Wang Y, Liu B (2021) Mhfc: multi-head feature collaboration for few-shot learning. In: Proceedings of the 29th ACM international conference on multimedia, pp 4193\u20134201","DOI":"10.1145\/3474085.3475553"},{"key":"11451_CR15","doi-asserted-by":"crossref","unstructured":"Simon C, Koniusz P, Nock R, Harandi M (2020) Adaptive subspaces for few-shot learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4136\u20134145","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"11451_CR16","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Adv Neural Inf Processing Syst 30"},{"key":"11451_CR17","doi-asserted-by":"crossref","unstructured":"Sung F, Yang Y, Zhang L, Xiang T, Torr PH, Hospedales TM (2018) Learning to compare: relation network for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1199\u20131208","DOI":"10.1109\/CVPR.2018.00131"},{"key":"11451_CR18","first-page":"1","volume":"19","author":"L Xing","year":"2022","unstructured":"Xing L, Ma Y, Cao W, Shao S, Liu W, Liu B (2022) Rethinking few-shot remote sensing scene classification: a good embedding is all you need? IEEE Geosci Remote Sens Lett 19:1\u20135","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"11451_CR19","first-page":"1","volume":"19","author":"L Xing","year":"2022","unstructured":"Xing L, Shao S, Ma Y, Wang Y, Liu W, Liu B (2022) Learning to cooperate: decision fusion method for few-shot remote-sensing scene classification. IEEE Geosci Remote Sens Lett 19:1\u20135","journal-title":"IEEE Geosci Remote Sens Lett"},{"issue":"2","key":"11451_CR20","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1007\/s11063-021-10684-7","volume":"54","author":"R Xu","year":"2022","unstructured":"Xu R, Liu B, Lu X, Zhang K, Liu W (2022) Dmh-fsl: dual-modal hypergraph for few-shot learning. Neural Process Lett 54(2):1317\u20131332","journal-title":"Neural Process Lett"},{"key":"11451_CR21","first-page":"1","volume":"60","author":"X Yao","year":"2021","unstructured":"Yao X, Cao Q, Feng X, Cheng G, Han J (2021) Scale-aware detailed matching for few-shot aerial image semantic segmentation. IEEE Trans Geosci Remote Sens 60:1\u201311","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"11451_CR22","doi-asserted-by":"crossref","unstructured":"Ye HJ, Hu H, Zhan DC, Sha F (2020) Few-shot learning via embedding adaptation with set-to-set functions. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8808\u20138817","DOI":"10.1109\/CVPR42600.2020.00883"},{"issue":"1","key":"11451_CR23","doi-asserted-by":"publisher","first-page":"108","DOI":"10.3390\/rs13010108","volume":"13","author":"P Zhang","year":"2020","unstructured":"Zhang P, Bai Y, Wang D, Bai B, Li Y (2020) Few-shot classification of aerial scene images via meta-learning. Remote Sens 13(1):108","journal-title":"Remote Sens"},{"issue":"21","key":"11451_CR24","doi-asserted-by":"publisher","first-page":"4200","DOI":"10.3390\/rs13214200","volume":"13","author":"P Zhang","year":"2021","unstructured":"Zhang P, Fan G, Wu C, Wang D, Li Y (2021) Task-adaptive embedding learning with dynamic kernel fusion for few-shot remote sensing scene classification. Remote Sens 13(21):4200","journal-title":"Remote Sens"},{"issue":"5","key":"11451_CR25","doi-asserted-by":"publisher","first-page":"1566","DOI":"10.3390\/s21051566","volume":"21","author":"P Zhang","year":"2021","unstructured":"Zhang P, Li Y, Wang D, Wang J (2021) Rs-sskd: self-supervision equipped with knowledge distillation for few-shot remote sensing scene classification. Sensors 21(5):1566","journal-title":"Sensors"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11451-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-024-11451-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11451-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T20:05:32Z","timestamp":1709237132000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-024-11451-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,5]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["11451"],"URL":"https:\/\/doi.org\/10.1007\/s11063-024-11451-0","relation":{},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,5]]},"assertion":[{"value":"20 December 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"2"}}