{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T23:04:42Z","timestamp":1748387082274,"version":"3.37.3"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"28","license":[{"start":{"date-parts":[[2023,8,5]],"date-time":"2023-08-05T00:00:00Z","timestamp":1691193600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,5]],"date-time":"2023-08-05T00:00:00Z","timestamp":1691193600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R & D Program of China","doi-asserted-by":"crossref","award":["2021ZD0110901"],"award-info":[{"award-number":["2021ZD0110901"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s00521-023-08787-4","type":"journal-article","created":{"date-parts":[[2023,8,5]],"date-time":"2023-08-05T09:01:31Z","timestamp":1691226091000},"page":"21275-21290","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Focus nuance and toward diversity: exploring domain-specific fine-grained few-shot recognition"],"prefix":"10.1007","volume":"35","author":[{"given":"Minghui","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxun","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,5]]},"reference":[{"key":"8787_CR1","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances neural information processing systems. 28"},{"issue":"21","key":"8787_CR2","doi-asserted-by":"publisher","first-page":"19061","DOI":"10.1007\/s00521-022-07510-z","volume":"34","author":"D Joshi","year":"2022","unstructured":"Joshi D, Singh TP, Joshi AK (2022) Deep learning-based localization and segmentation of wrist fractures on x-ray radiographs. Neural Comput Appl 34(21):19061\u201319077","journal-title":"Neural Comput Appl"},{"key":"8787_CR3","doi-asserted-by":"publisher","first-page":"7957","DOI":"10.1007\/s00521-019-04691-y","volume":"32","author":"A Wadhawan","year":"2020","unstructured":"Wadhawan A, Kumar P (2020) Deep learning-based sign language recognition system for static signs. Neural Comput Appl 32:7957\u20137968","journal-title":"Neural Comput Appl"},{"key":"8787_CR4","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems. 25"},{"key":"8787_CR5","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"8787_CR6","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"8787_CR7","unstructured":"Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. In: ICML Deep learning workshop. vol. 2, p. 0. Lille"},{"key":"8787_CR8","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Advances in neural information processing systems. 30"},{"key":"8787_CR9","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":"8787_CR10","unstructured":"Vinyals O, Blundell C, Lillicrap T, Wierstra D et al (2016) Matching networks for one shot learning. In: Advances in neural information processing systems. 29"},{"key":"8787_CR11","doi-asserted-by":"crossref","unstructured":"Zhang B, Li X, Ye Y, Huang Z, Zhang L (2021) Prototype completion with primitive knowledge for few-shot learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 3754\u20133762","DOI":"10.1109\/CVPR46437.2021.00375"},{"key":"8787_CR12","doi-asserted-by":"crossref","unstructured":"Liu B, Cao Y, Lin Y, Li Q, Zhang Z, Long M, Hu H (2020) Negative margin matters: Understanding margin in few-shot classification. In: European conference on computer vision. pp. 438\u2013455. Springer","DOI":"10.1007\/978-3-030-58548-8_26"},{"key":"8787_CR13","doi-asserted-by":"crossref","unstructured":"Liu C, Fu Y, Xu C, Yang S, Li J, Wang C, Zhang L (2021) Learning a few-shot embedding model with contrastive learning. In: Proceedings of the AAAI conference on artificial intelligence. 35:8635\u20138643","DOI":"10.1609\/aaai.v35i10.17047"},{"key":"8787_CR14","doi-asserted-by":"crossref","unstructured":"Xie J, Long F, Lv J, Wang Q, Li P (2022) Joint distribution matters: Deep brownian distance covariance for few-shot classification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 7972\u20137981","DOI":"10.1109\/CVPR52688.2022.00781"},{"issue":"12","key":"8787_CR15","doi-asserted-by":"publisher","first-page":"8927","DOI":"10.1109\/TPAMI.2021.3126648","volume":"44","author":"X-S Wei","year":"2021","unstructured":"Wei X-S, Song Y-Z, Mac Aodha O, Wu J, Peng Y, Tang J, Yang J, Belongie S (2021) Fine-grained image analysis with deep learning: a survey. IEEE Trans Pattern Anal Mach Intell 44(12):8927\u20138948","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8787_CR16","doi-asserted-by":"crossref","unstructured":"Li W, Xu J, Huo J, Wang L, Gao Y, Luo J (2019) Distribution consistency based covariance metric networks for few-shot learning. In: Proceedings of the AAAI conference on artificial intelligence. 33:8642\u20138649","DOI":"10.1609\/aaai.v33i01.33018642"},{"key":"8787_CR17","doi-asserted-by":"crossref","unstructured":"Dong C, Li W, Huo J, Gu Z, Gao Y (2021) Learning task-aware local representations for few-shot learning. In: Proceedings of the twenty-ninth international conference on international joint conferences on artificial intelligence. pp. 716\u2013722","DOI":"10.24963\/ijcai.2020\/100"},{"key":"8787_CR18","doi-asserted-by":"crossref","unstructured":"Li W, Wang L, Xu J, Huo J, Gao Y, Luo J (2019) Revisiting local descriptor based image-to-class measure for few-shot learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 7260\u20137268","DOI":"10.1109\/CVPR.2019.00743"},{"key":"8787_CR19","doi-asserted-by":"crossref","unstructured":"Wertheimer D, Hariharan B (2019) Few-shot learning with localization in realistic settings. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 6558\u20136567","DOI":"10.1109\/CVPR.2019.00672"},{"key":"8787_CR20","doi-asserted-by":"crossref","unstructured":"Yan S, Zhang S, He X (2019) A dual attention network with semantic embedding for few-shot learning. In: AAAI, 9079\u20139086","DOI":"10.1609\/aaai.v33i01.33019079"},{"key":"8787_CR21","doi-asserted-by":"crossref","unstructured":"Behera A, Wharton Z, Hewage PR, Bera A (2021) Context-aware attentional pooling (cap) for fine-grained visual classification. In: Proceedings of the AAAI conference on artificial intelligence. 35:929\u2013937","DOI":"10.1609\/aaai.v35i2.16176"},{"issue":"4","key":"8787_CR22","doi-asserted-by":"publisher","first-page":"3588","DOI":"10.1109\/TIE.2020.2977553","volume":"68","author":"X Sun","year":"2020","unstructured":"Sun X, Xv H, Dong J, Zhou H, Chen C, Li Q (2020) Few-shot learning for domain-specific fine-grained image classification. IEEE Trans Ind Electron 68(4):3588\u20133598","journal-title":"IEEE Trans Ind Electron"},{"key":"8787_CR23","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.compag.2018.01.009","volume":"145","author":"KP Ferentinos","year":"2018","unstructured":"Ferentinos KP (2018) Deep learning models for plant disease detection and diagnosis. Comput Electron Agric 145:311\u2013318","journal-title":"Comput Electron Agric"},{"issue":"1","key":"8787_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13007-019-0475-z","volume":"15","author":"MG Selvaraj","year":"2019","unstructured":"Selvaraj MG, Vergara A, Ruiz H, Safari N, Elayabalan S, Ocimati W, Blomme G (2019) Ai-powered banana diseases and pest detection. Plant Methods 15(1):1\u201311","journal-title":"Plant Methods"},{"issue":"3","key":"8787_CR25","doi-asserted-by":"publisher","first-page":"47","DOI":"10.3390\/technologies9030047","volume":"9","author":"T Aboneh","year":"2021","unstructured":"Aboneh T, Rorissa A, Srinivasagan R, Gemechu A (2021) Computer vision framework for wheat disease identification and classification using jetson gpu infrastructure. Technologies 9(3):47","journal-title":"Technologies"},{"key":"8787_CR26","unstructured":"Santoro A, Bartunov S, Botvinick M, Wierstra D, Lillicrap T (2016) Meta-learning with memory-augmented neural networks. In: International conference on machine learning. pp. 1842\u20131850 . PMLR"},{"key":"8787_CR27","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning. pp. 1126\u20131135. PMLR"},{"key":"8787_CR28","unstructured":"Ravi S, Larochelle H (2016) Optimization as a model for few-shot learning"},{"key":"8787_CR29","unstructured":"Abbas M, Xiao Q, Chen L, Chen P-Y, Chen T (2022) Sharp-maml: sharpness-aware model-agnostic meta learning. arXiv preprint arXiv:2206.03996"},{"key":"8787_CR30","unstructured":"Chen Y, Wang X, Liu Z, Xu H, Darrell T (2020) A new meta-baseline for few-shot learning"},{"key":"8787_CR31","doi-asserted-by":"crossref","unstructured":"Fu J, Zheng H, Mei T (2017) Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4438\u20134446","DOI":"10.1109\/CVPR.2017.476"},{"key":"8787_CR32","doi-asserted-by":"publisher","first-page":"9295","DOI":"10.1007\/s00521-019-04281-y","volume":"31","author":"J Leng","year":"2019","unstructured":"Leng J, Liu Y, Chen S (2019) Context-aware attention network for image recognition. Neural Comput Appl 31:9295\u20139305","journal-title":"Neural Comput Appl"},{"key":"8787_CR33","doi-asserted-by":"crossref","unstructured":"Zheng H, Fu J, Mei T, Luo J (2017) Learning multi-attention convolutional neural network for fine-grained image recognition. In: Proceedings of the IEEE international conference on computer vision. pp. 5209\u20135217","DOI":"10.1109\/ICCV.2017.557"},{"key":"8787_CR34","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems. 30"},{"issue":"6","key":"8787_CR35","doi-asserted-by":"publisher","first-page":"2868","DOI":"10.1109\/TIP.2017.2688133","volume":"26","author":"X-S Wei","year":"2017","unstructured":"Wei X-S, Luo J-H, Wu J, Zhou Z-H (2017) Selective convolutional descriptor aggregation for fine-grained image retrieval. IEEE Trans Image Process 26(6):2868\u20132881","journal-title":"IEEE Trans Image Process"},{"key":"8787_CR36","doi-asserted-by":"crossref","unstructured":"Zhu L, Yang Y (2018) Compound memory networks for few-shot video classification. In: Proceedings of the European conference on computer vision (ECCV). pp. 751\u2013766","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"8787_CR37","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"3","key":"8787_CR38","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon CE (1948) A mathematical theory of communication. The Bell Syst Tech J 27(3):379\u2013423","journal-title":"The Bell Syst Tech J"},{"key":"8787_CR39","doi-asserted-by":"crossref","unstructured":"Cui S, Wang S, Zhuo J, Li L, Huang Q, Tian Q (2020) Towards discriminability and diversity: Batch nuclear-norm maximization under label insufficient situations. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 3941\u20133950","DOI":"10.1109\/CVPR42600.2020.00400"},{"key":"8787_CR40","doi-asserted-by":"crossref","unstructured":"Song J, Shen C, Yang Y, Liu Y, Song M (2018) Transductive unbiased embedding for zero-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1024\u20131033","DOI":"10.1109\/CVPR.2018.00113"},{"key":"8787_CR41","doi-asserted-by":"crossref","unstructured":"Zhuo J, Wang S, Cui S, Huang Q (2019) Unsupervised open domain recognition by semantic discrepancy minimization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 750\u2013759","DOI":"10.1109\/CVPR.2019.00084"},{"key":"8787_CR42","doi-asserted-by":"crossref","unstructured":"Zou Y, Yu Z, Liu X, Kumar B, Wang J (2019) Confidence regularized self-training. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 5982\u20135991","DOI":"10.1109\/ICCV.2019.00608"},{"key":"8787_CR43","doi-asserted-by":"crossref","unstructured":"Zou Y, Yu Z, Kumar B, Wang J (2018) Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: Proceedings of the European conference on computer vision (ECCV). pp. 289\u2013305","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"8787_CR44","unstructured":"Fazel M (2002) Matrix rank minimization with applications. PhD thesis, PhD thesis, Stanford University"},{"issue":"3","key":"8787_CR45","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1137\/070697835","volume":"52","author":"B Recht","year":"2010","unstructured":"Recht B, Fazel M, Parrilo PA (2010) Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM Rev 52(3):471\u2013501","journal-title":"SIAM Rev"},{"key":"8787_CR46","unstructured":"Srebro N, Rennie J, Jaakkola T(2004) Maximum-margin matrix factorization. In: Advances in neural information processing systems. 17"},{"key":"8787_CR47","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on computer vision and pattern recognition. pp. 248\u2013255. IEEE","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"8787_CR48","unstructured":"Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-ucsd birds-200-2011 dataset"},{"key":"8787_CR49","doi-asserted-by":"crossref","unstructured":"Sun Q, Liu Y, Chua T-S, Schiele B (2019) Meta-transfer learning for few-shot learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 403\u2013412","DOI":"10.1109\/CVPR.2019.00049"},{"key":"8787_CR50","doi-asserted-by":"crossref","unstructured":"Liu Y, Schiele B, Sun Q (2020) An ensemble of epoch-wise empirical bayes for few-shot learning. In: Computer Vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVI 16, pp. 404\u2013421. Springer","DOI":"10.1007\/978-3-030-58517-4_24"},{"key":"8787_CR51","unstructured":"Park S-J, Han S, Baek J-W, Kim I, Song J, Lee HB, Han J-J, Hwang SJ (2020) Meta variance transfer: Learning to augment from the others. In: International conference on machine learning, pp. 7510\u20137520 . PMLR"},{"issue":"9","key":"8787_CR52","doi-asserted-by":"publisher","first-page":"4594","DOI":"10.1109\/TIP.2019.2910052","volume":"28","author":"Z Chen","year":"2019","unstructured":"Chen Z, Fu Y, Zhang Y, Jiang Y-G, Xue X, Sigal L (2019) Multi-level semantic feature augmentation for one-shot learning. IEEE Trans Image Process 28(9):4594\u20134605","journal-title":"IEEE Trans Image Process"},{"key":"8787_CR53","unstructured":"Chen W-Y, Liu Y-C, Kira Z, Wang Y-CF, Huang J-B (2019) A closer look at few-shot classification. arXiv preprint arXiv:1904.04232"},{"key":"8787_CR54","doi-asserted-by":"crossref","unstructured":"Ye H-J, Hu H, Zhan D-C, 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"},{"key":"8787_CR55","doi-asserted-by":"crossref","unstructured":"Zhang C, Cai Y, Lin G, Shen C (2020) Deepemd: Few-shot image classification with differentiable earth mover\u2019s distance and structured classifiers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 12203\u201312213","DOI":"10.1109\/CVPR42600.2020.01222"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08787-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08787-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08787-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T00:32:54Z","timestamp":1693355574000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08787-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,5]]},"references-count":55,"journal-issue":{"issue":"28","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["8787"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08787-4","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2023,8,5]]},"assertion":[{"value":"14 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declared that they have no conflicts of interest to this work. We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}