{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T15:04:16Z","timestamp":1781967856762,"version":"3.54.5"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T00:00:00Z","timestamp":1738108800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T00:00:00Z","timestamp":1738108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771334"],"award-info":[{"award-number":["61771334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771334"],"award-info":[{"award-number":["61771334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771334"],"award-info":[{"award-number":["61771334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Aiming to detect novel objects from only a few annotated samples, few-shot object detection (FSOD) has undergone remarkable development. Previous works rarely pay attention to the perspective of gradient propagation to optimize existing methods, therefore failing to make full use of information for novel objects in gradient propagation. We propose a method to solve this problem based on two-stage fine-tuning. A domain adaptation module with multi-constraints is used to promote the spread of gradients, a classification promotion network is used to improve the effect of classification, and a multi-path mask head is added to enrich RoI features. Experiments on PASCAL VOC and COCO datasets show that our model significantly raises the performance compared with previous methods (up to 1\u20135<jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>$$\\%$$<\/jats:tex-math>\n                <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mo>%<\/mml:mo>\n                <\/mml:math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula> in average).<\/jats:p>","DOI":"10.1007\/s11063-025-11727-z","type":"journal-article","created":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T00:30:20Z","timestamp":1738197020000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Few-Shot Object Detection Based on Global Domain Adaptation Strategy"],"prefix":"10.1007","volume":"57","author":[{"given":"Xiaolin","family":"Gong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youpeng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daqing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongtao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,29]]},"reference":[{"issue":"6","key":"11727_CR1","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11727_CR2","doi-asserted-by":"crossref","unstructured":"He D, Qiu Y, Miao J, Zou Z, Li K, Ren C, Shen G (2022) Improved mask R-CNN for obstacle detection of rail transit. Measurement 110728","DOI":"10.1016\/j.measurement.2022.110728"},{"key":"11727_CR3","doi-asserted-by":"crossref","unstructured":"Mathew MP, Mahesh TY (2021) Leaf-based disease detection in bell pepper plant using YOLO v5. Signal Image Video Process 1\u20137","DOI":"10.1007\/s11760-021-02024-y"},{"issue":"2","key":"11727_CR4","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1007\/s11760-021-01981-8","volume":"16","author":"Y Zou","year":"2022","unstructured":"Zou Y, Zhang Y, Yan J, Jiang X, Huang T, Fan H, Cui Z (2022) License plate detection and recognition based on YOLOv3 and ILPRNET. SIViP 16(2):473\u2013480","journal-title":"SIViP"},{"key":"11727_CR5","doi-asserted-by":"crossref","unstructured":"\u00c7elik Y, Ba\u015faran E, Dilay Y (2022) Identification of durum wheat grains by using hybrid convolution neural network and deep features. Signal Image Video Process 1\u20138","DOI":"10.1007\/s11760-021-02094-y"},{"issue":"11","key":"11727_CR6","doi-asserted-by":"publisher","first-page":"5652","DOI":"10.1109\/TIP.2018.2861573","volume":"27","author":"S Rahman","year":"2018","unstructured":"Rahman S, Khan S, Porikli F (2018) A unified approach for conventional zero-shot, generalized zero-shot, and few-shot learning. IEEE Trans Image Process 27(11):5652\u20135667","journal-title":"IEEE Trans Image Process"},{"key":"11727_CR7","doi-asserted-by":"crossref","unstructured":"Chen H, Wang Y, Wang G, Qiao Y (2018) LSTD: a low-shot transfer detector for object detection. In: Proceedings of the AAAI conference on artificial intelligence, vol\u00a032","DOI":"10.1609\/aaai.v32i1.11716"},{"key":"11727_CR8","doi-asserted-by":"crossref","unstructured":"Wang Y-X, Ramanan D, Hebert M (2019) Meta-learning to detect rare objects. In: 2019 IEEE\/CVF international conference on computer vision (ICCV), pp 9924\u20139933","DOI":"10.1109\/ICCV.2019.01002"},{"key":"11727_CR9","unstructured":"Liu L, Wang B, Kuang Z, Xue J-H, Chen Y, Yang W, Liao Q, Zhang W (2021) GenDet: meta learning to generate detectors from few shots. IEEE Trans Neural Netw Learn Syst 1\u201313"},{"key":"11727_CR10","doi-asserted-by":"crossref","unstructured":"Karlinsky L, Shtok J, Harary S, Schwartz E, Aides A, Feris R, Giryes R, Bronstein AM (2019) RepMet: representative-based metric learning for classification and few-shot object detection. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 5192\u20135201","DOI":"10.1109\/CVPR.2019.00534"},{"key":"11727_CR11","doi-asserted-by":"crossref","unstructured":"Li B, Yang B, Liu C, Liu F, Ji R, Ye Q (2021) Beyond max-margin: class margin equilibrium for few-shot object detection. In 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7359\u20137368","DOI":"10.1109\/CVPR46437.2021.00728"},{"key":"11727_CR12","unstructured":"Wang X, Huang TE, Darrell T, Gonzalez JE, Yu F (2020) Frustratingly simple few-shot object detection. In: International conference on machine learning. PMLR, pp 9919\u20139928"},{"key":"11727_CR13","unstructured":"Li S, Song W, Li S, Hao A, Qin H (2020) Meta-retinanet for few-shot object detection. In: BMVC, pp 1\u201312"},{"key":"11727_CR14","doi-asserted-by":"crossref","unstructured":"Sun B, Li B, Cai S, Yuan Y, Zhang C (2021) Fsce: few-shot object detection via contrastive proposal encoding. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7348\u20137358","DOI":"10.1109\/CVPR46437.2021.00727"},{"key":"11727_CR15","doi-asserted-by":"crossref","unstructured":"Zhang W, Wang Y-X (2021) Hallucination improves few-shot object detection. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 13003\u201313012","DOI":"10.1109\/CVPR46437.2021.01281"},{"key":"11727_CR16","doi-asserted-by":"crossref","unstructured":"Qiao L, Zhao Y, Li Z, Qiu X, Wu J, Zhang C (2021) DeFRCN: decoupled faster R-CNN for few-shot object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8681\u20138690","DOI":"10.1109\/ICCV48922.2021.00856"},{"key":"11727_CR17","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"issue":"3","key":"11727_CR18","doi-asserted-by":"publisher","first-page":"1785","DOI":"10.1109\/TIT.2019.2950717","volume":"66","author":"Q Qing","year":"2020","unstructured":"Qing Q, Zhang Y, Eldar YC, Wright J (2020) Convolutional phase retrieval via gradient descent. IEEE Trans Inf Theory 66(3):1785\u20131821","journal-title":"IEEE Trans Inf Theory"},{"key":"11727_CR19","first-page":"1","volume":"70","author":"C Zhu","year":"2021","unstructured":"Zhu C, Chen Z, Zhao R, Wang J, Yan R (2021) Decoupled feature-temporal CNN: explaining deep learning-based machine health monitoring. IEEE Trans Instrum Meas 70:1\u201313","journal-title":"IEEE Trans Instrum Meas"},{"key":"11727_CR20","doi-asserted-by":"crossref","unstructured":"Wang Y, Zhang R, Zhang S, Li M, Xia YY, Zhang XS, Liu SL (2021) Domain-specific suppression for adaptive object detection. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 9598\u20139607","DOI":"10.1109\/CVPR46437.2021.00948"},{"key":"11727_CR21","doi-asserted-by":"crossref","unstructured":"Huang W-C, Chung P-C, Tsai H-W, Chow N-H, Juang Y-Z, Tsai H-H, Lin S-H, Wang C-H (2019) Automatic hcc detection using convolutional network with multi-magnification input images. In: 2019 IEEE international conference on artificial intelligence circuits and systems (AICAS), pp 194\u2013198","DOI":"10.1109\/AICAS.2019.8771535"},{"issue":"7","key":"11727_CR22","doi-asserted-by":"publisher","first-page":"1631","DOI":"10.1007\/s13042-018-0842-5","volume":"10","author":"X Wang","year":"2019","unstructured":"Wang X, Bao A, Cheng Y, Qiang Yu (2019) Weight-sharing multi-stage multi-scale ensemble convolutional neural network. Int J Mach Learn Cybern 10(7):1631\u20131642","journal-title":"Int J Mach Learn Cybern"},{"issue":"7","key":"11727_CR23","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1007\/s11760-020-01680-w","volume":"14","author":"H Mliki","year":"2020","unstructured":"Mliki H, Dammak S, Fendri E (2020) An improved multi-scale face detection using convolutional neural network. SIViP 14(7):1345\u20131353","journal-title":"SIViP"},{"key":"11727_CR24","doi-asserted-by":"publisher","first-page":"3956","DOI":"10.1109\/TIP.2021.3064258","volume":"30","author":"S-J Wang","year":"2021","unstructured":"Wang S-J, He Y, Li J, Xiaolan F (2021) Mesnet: a convolutional neural network for spotting multi-scale micro-expression intervals in long videos. IEEE Trans Image Process 30:3956\u20133969","journal-title":"IEEE Trans Image Process"},{"key":"11727_CR25","doi-asserted-by":"publisher","first-page":"8823","DOI":"10.1109\/TIP.2021.3120675","volume":"30","author":"S Yang","year":"2021","unstructured":"Yang S, Hou J, Jia Y, Mei S, Qian D (2021) Superpixel-guided discriminative low-rank representation of hyperspectral images for classification. IEEE Trans Image Process 30:8823\u20138835","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"11727_CR26","doi-asserted-by":"publisher","first-page":"2714","DOI":"10.1109\/JBHI.2022.3159031","volume":"26","author":"Y Liang","year":"2022","unstructured":"Liang Y, Gaoxu X (2022) Multi-level functional connectivity fusion classification framework for brain disease diagnosis. IEEE J Biomed Health Inform 26(6):2714\u20132725","journal-title":"IEEE J Biomed Health Inform"},{"issue":"5","key":"11727_CR27","doi-asserted-by":"publisher","first-page":"1405","DOI":"10.1109\/JBHI.2019.2949075","volume":"24","author":"WM Liao","year":"2020","unstructured":"Liao WM, Zou BJ, Zhao RC, Chen YQ, He ZY, Zhou MJ (2020) Clinical interpretable deep learning model for glaucoma diagnosis. IEEE J Biomed Health Inform 24(5):1405\u20131412","journal-title":"IEEE J Biomed Health Inform"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-025-11727-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-025-11727-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-025-11727-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T12:46:25Z","timestamp":1741697185000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-025-11727-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,29]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["11727"],"URL":"https:\/\/doi.org\/10.1007\/s11063-025-11727-z","relation":{},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,29]]},"assertion":[{"value":"6 January 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This work was supported by National Natural Science Foundation of China (61771334), and Tianjin Intelligent Security Industry Chain Technology Adaptation and Application Project under Grant 18ZXZNGX00320. Other conflict of interest are not included.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This paper is not applicable for both human or animal studies.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"12"}}