{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T19:29:47Z","timestamp":1780687787332,"version":"3.54.1"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T00:00:00Z","timestamp":1714089600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003471","name":"Harbin Engineering University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003471","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>The meta-learning methods have been widely used to solve the problem of few-shot learning. Generally, meta-learners are trained on a variety of tasks and then generalized to novel tasks.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>However, existing meta-learning methods do not consider the relationship between meta-tasks and novel tasks during the meta-training period, so that initial models of the meta-learner provide less useful meta-knowledge for the novel tasks. This leads to a weak generalization ability on novel tasks. Meanwhile, different initial models contain different meta-knowledge, which leads to certain differences in the learning effect of novel tasks during the meta-testing period. Therefore, this article puts forward a meta-optimization method based on situational meta-task construction and cooperation of multiple initial models. First, during the meta-training period, a method of constructing situational meta-task is proposed, and the selected candidate task sets provide more effective meta-knowledge for novel tasks. Then, during the meta-testing period, an ensemble model method based on meta-optimization is proposed to minimize the loss of inter-model cooperation in prediction, so that multiple models cooperation can realize the learning of novel tasks.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The above-mentioned methods are applied to popular few-shot character datasets and image recognition datasets. Furthermore, the experiment results indicate that the proposed method achieves good effects in few-shot classification tasks.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>In future work, we will extend our methods to provide more generalized and useful meta-knowledge to the model during the meta-training period when the novel few-shot tasks are completely invisible.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnbot.2024.1391247","type":"journal-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T04:56:34Z","timestamp":1714107394000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["The meta-learning method for the ensemble model based on situational meta-task"],"prefix":"10.3389","volume":"18","author":[{"given":"Zhengchao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianke","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nianbin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,4,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"8717","DOI":"10.1109\/TPAMI.2018.2889052","article-title":"Deep audio-visual speech recognition","volume":"44","author":"Afouras","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B2","article-title":"\u201cMeta-learning with differentiable closed-form solvers,\u201d","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Bertinetto","year":"2019"},{"key":"B3","first-page":"721","article-title":"\u201cTadam: task dependent adaptive metric for improved few-shot learning,\u201d","volume-title":"32nd Conference on Neural Information Processing Systems (NIPS)","author":"Boris","year":"2018"},{"key":"B4","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn"},{"key":"B5","doi-asserted-by":"publisher","first-page":"4594","DOI":"10.1109\/TIP.2019.2910052","article-title":"Multi-level semantic feature augmentation for one-shot learning","volume":"28","author":"Chen","year":"2019","journal-title":"IEEE Transact. Image Process"},{"key":"B6","first-page":"12362","article-title":"\u201cMeta-learning of neural architectures for few-shot learning,\u201d","author":"Elsken","year":"2020","journal-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition"},{"key":"B7","first-page":"1856","article-title":"\u201cModel-agnostic meta-learning for fast adaptation of deep networks,\u201d","volume-title":"34th International Conference on Machine Learning, ICML","author":"Finn","year":"2017"},{"key":"B8","author":"Fort","year":"2017","journal-title":"Gaussian Prototypical Networks for Few-Shot learning on Omniglot"},{"key":"B9","first-page":"148","article-title":"Experiment with a new boosting algorithm","volume":"96","author":"Freund","year":"1996","journal-title":"Morgan Kaufmann"},{"key":"B10","doi-asserted-by":"publisher","first-page":"105151","DOI":"10.1016\/j.engappai.2022.105151","article-title":"Ensemble deep learning: a review","volume":"115","author":"Ganaie","year":"2022","journal-title":"Eng. Appl. Artif. Intell"},{"key":"B11","doi-asserted-by":"publisher","first-page":"131702","DOI":"10.1007\/s11704-021-1237-4","article-title":"Meta-bn net for few-shot learning","volume":"17","author":"Gao","year":"2023","journal-title":"Front. Comp. Sci"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-023-00279-4","article-title":"Few-shot and meta-learning methods for image understanding: a survey","author":"He","year":"2023","journal-title":"Int. J. Multim. Inf"},{"key":"B13","doi-asserted-by":"publisher","first-page":"5149","DOI":"10.1109\/TPAMI.2021.3079209","article-title":"Meta-learning in neural networks: a survey","volume":"44","author":"Hospedales","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B14","article-title":"\u201cEmpirical Bayes transductive meta-learning with synthetic gradients,\u201d","author":"Hu","year":"2020","journal-title":"8th International Conference on Learning Representations, ICLR 2020"},{"key":"B15","doi-asserted-by":"publisher","first-page":"106726","DOI":"10.1016\/j.compbiomed.2023.106726","article-title":"A review of deep learning-based multiple-lesion recognition from medical images: classification, detection and segmentation","volume":"157","author":"Jiang","year":"2023","journal-title":"Comput. Biol. Med"},{"key":"B16","first-page":"1467","article-title":"\u201cDeep neural decision forests,\u201d","volume-title":"IEEE International Conference on Computer Vision","author":"Kontschieder","year":"2015"},{"key":"B17","first-page":"2568","article-title":"\u201cOne shot learning of simple visual concepts,\u201d","volume-title":"Proceedings of the 33rd Annual Meeting of the Cognitive Science Society, CogSci","author":"Lake","year":"2011"},{"key":"B18","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":"B19","first-page":"10657","article-title":"\u201cMeta-learning with differentiable convex optimization,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer vision and Pattern Recognition","author":"Lee","year":"2019"},{"key":"B20","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1016\/j.neucom.2020.05.114","article-title":"A concise review of recent few-shot meta-learning methods","volume":"456","author":"Li","year":"2021","journal-title":"Neurocomputing"},{"key":"B21","author":"Li","year":"2017","journal-title":"Meta-sgd: Learning to Learn Quickly for Few-Shot Learning"},{"key":"B22","first-page":"9250","article-title":"\u201cDense classification and implanting for few-shot learning,\u201d","volume-title":"32nd IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lifchitz","year":"2019"},{"key":"B23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58452-8_43","article-title":"\u201cPrototype rectification for few-shot learning,\u201d","volume-title":"Computer Vision- ECCV:16th European Conference","author":"Liu","year":"2020"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1753","DOI":"10.3390\/electronics11111752","article-title":"Few-shot image classification: current status and research trends","volume":"11","author":"Liu","year":"2022","journal-title":"Electronics"},{"key":"B25","doi-asserted-by":"publisher","first-page":"109480","DOI":"10.1016\/j.patcog.2023.109480","article-title":"A survey on machine learning from few samples","volume":"139","author":"Lu","year":"2023","journal-title":"Pattern Recognit"},{"key":"B26","volume-title":"Meta-Learning With Temporal Convolutions","author":"Mishra","year":"2017"},{"key":"B27","author":"Nichol","year":"2018","journal-title":"On First-Order Meta-Learning Algorithms"},{"key":"B28","article-title":"\u201cA simple neural attentive meta-learner,\u201d","author":"Nikhil","year":"2018","journal-title":"6th International Conference on Learning Representations, ICLR 2018"},{"key":"B29","article-title":"\u201cMeta-learning with implicit gradients,\u201d","volume-title":"33rd Conference on Neural Information Processing Systems (NIPS)","author":"Rajeswaran","year":"2019"},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58574-7_8","article-title":"\u201cEmbedding propagation: smoother manifold for few-shot classification,\u201d","volume-title":"Computer Vision-ECCV: 16th European Conference","author":"Rodr\u00edguez","year":"2020"},{"key":"B31","first-page":"5446","article-title":"\u201cDisan: directional self-attention network for rnn\/cnn-free language understanding,\u201d","volume-title":"32nd AAAI Conference on Artificial Intelligence, AAAI","author":"Shen","year":"2018"},{"key":"B32","first-page":"4078","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"Snell","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B33","doi-asserted-by":"publisher","first-page":"3582688","DOI":"10.1145\/3582688","article-title":"A comprehensive survey of few-shot learning: evolution, applications, challenges, and opportunities. ACM Comp","volume":"55","author":"Song","year":"2023","journal-title":"Surv"},{"key":"B34","first-page":"403","article-title":"\u201cMeta-transfer learning for few-shot learning,\u201d","volume-title":"32nd IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Sun","year":"2019"},{"key":"B35","author":"Vanschoren","year":"2018","journal-title":"Meta-learning: A Survey."},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357847","article-title":"Advances and challenges in meta-learning: a technical review","author":"Vettoruzzo","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B37","first-page":"3637","article-title":"Matching networks for one shot learning","author":"Vinyals","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3386252","article-title":"Generalizing from a few examples: a survey on few-shot learning","volume":"53","author":"Wang","year":"2020","journal-title":"ACM Comp. Surv"},{"key":"B39","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neur. Netw"},{"key":"B40","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1109\/TPAMI.2019.2932058","article-title":"Hierarchical deep click feature prediction for fine-grained image recognition","volume":"44","author":"Yu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B41","doi-asserted-by":"publisher","first-page":"2024029","DOI":"10.3934\/mbe.2024029","article-title":"Few-shot learning based on deep learning: a survey","volume":"21","author":"Zeng","year":"2024","journal-title":"Math. Biosci. Eng"},{"key":"B42","doi-asserted-by":"publisher","first-page":"5632","DOI":"10.1109\/TPAMI.2022.3217373","article-title":"Deepemd: differentiable earth mover's distance for few-shot learning","volume":"45","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B43","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1109\/TAFFC.2019.2947464","article-title":"Spontaneous speech emotion recognition using multiscale deep convolutional lstm","volume":"13","author":"Zhang","year":"2019","journal-title":"IEEE Transact. Affect. Comp"},{"key":"B44","volume-title":"Deep Meta-Learning: Learning to Learn in the Concept Space","author":"Zhou","year":"2018"},{"key":"B45","first-page":"4624","article-title":"\u201cLearning to select base classes for few-shot classification,\u201d","author":"Zhou","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B46","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2017\/497","article-title":"\u201cDeep forest: towards an alternative to deep neural networks,\u201d","volume-title":"26th International Joint Conference on Artificial Intelligence (IJCAI)","author":"Zhou","year":"2017"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1391247\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T04:56:52Z","timestamp":1714107412000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1391247\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,26]]},"references-count":46,"alternative-id":["10.3389\/fnbot.2024.1391247"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1391247","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,26]]},"article-number":"1391247"}}