{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:27:48Z","timestamp":1759332468678,"version":"3.37.3"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T00:00:00Z","timestamp":1570665600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T00:00:00Z","timestamp":1570665600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National Key R&D Program of China","award":["2018YFB1004300"],"award-info":[{"award-number":["2018YFB1004300"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61773198","61751306"],"award-info":[{"award-number":["61773198","61751306"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61632004"],"award-info":[{"award-number":["61632004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s10994-019-05838-7","type":"journal-article","created":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T20:03:41Z","timestamp":1570737821000},"page":"643-664","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach"],"prefix":"10.1007","volume":"109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1173-1880","authenticated-orcid":false,"given":"Han-Jia","family":"Ye","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang-Rong","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"De-Chuan","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,10]]},"reference":[{"key":"5838_CR1","first-page":"50:1","volume":"19","author":"A Achille","year":"2018","unstructured":"Achille, A., & Soatto, S. (2018). Emergence of invariance and disentanglement in deep representations. Journal of Machine Learning Research, 19, 50:1\u201350:34.","journal-title":"Journal of Machine Learning Research"},{"key":"5838_CR2","first-page":"3981","volume":"29","author":"M Andrychowicz","year":"2016","unstructured":"Andrychowicz, M., Denil, M., Colmenarejo, S. G., Hoffman, M. W., Pfau, D., Schaul, T., et al. (2016). Learning to learn by gradient descent by gradient descent. Advances in Neural Information Processing Systems, 29, 3981\u20133989.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5838_CR3","unstructured":"Antoniou, A., Edwards, H., & Storkey, A. J. (2018). How to train your MAML. CoRR \narXiv:1810.09502\n\n."},{"key":"5838_CR4","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1613\/jair.731","volume":"12","author":"J Baxter","year":"2000","unstructured":"Baxter, J. (2000). A model of inductive bias learning. Journal of Artificial Intelligence Research, 12, 149\u2013198.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"5838_CR5","unstructured":"Chen, W. Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., & Huang, J. B. (2019). A closer look at few-shot classification. CoRR \narXiv:1904.04232\n\n."},{"key":"5838_CR6","unstructured":"Clavera, I., Nagabandi, A., Fearing, R.S., Abbeel, P., Levine, S., & Finn, C. (2018). Learning to adapt: Meta-learning for model-based control. CoRR \narXiv:1803.11347\n\n."},{"key":"5838_CR7","unstructured":"Dai, W. Z., Muggleton, S., Wen, J., Tamaddoni-Nezhad, A., & Zhou, Z. H. (2017). Logical vision: One-shot meta-interpretive learning from real images. In Proceedings of the 27th international conference on inductive logic programming, Orl\u00e9ans, France (pp. 46\u201362)."},{"key":"5838_CR8","unstructured":"Deleu, T., & Bengio, Y. (2018). The effects of negative adaptation in model-agnostic meta-learning. CoRR \narXiv:1812.02159\n\n."},{"key":"5838_CR9","first-page":"10190","volume":"31","author":"G Denevi","year":"2018","unstructured":"Denevi, G., Ciliberto, C., Stamos, D., & Pontil, M. (2018). Learning to learn around A common mean. Advances in Neural Information Processing Systems, 31, 10190\u201310200.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5838_CR10","unstructured":"Finn, C., Abbeel, P., & Levine, S. (2017a). Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the 34th international conference on machine learning, Sydney, Australia (pp. 1126\u20131135)."},{"key":"5838_CR11","unstructured":"Finn, C., & Levine, S. (2018). Meta-learning and universality: Deep representations and gradient descent can approximate any learning algorithm. In Proceeding of the 6th international conference on learning representations, Vancouver, Canada."},{"key":"5838_CR12","first-page":"9537","volume":"31","author":"C Finn","year":"2018","unstructured":"Finn, C., Xu, K., & Levine, S. (2018). Probabilistic model-agnostic meta-learning. Advances in Neural Information Processing Systems, 31, 9537\u20139548.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5838_CR13","unstructured":"Finn, C., Yu, T., Zhang, T., Abbeel, P., & Levine, S. (2017b). One-shot visual imitation learning via meta-learning. In Proceedings of the 1st annual conference on robot learning, Mountain View, CA (pp. 357\u2013368)."},{"key":"5838_CR14","unstructured":"Franceschi, L., Donini, M., Frasconi, P., & Pontil, M. (2017). A bridge between hyperparameter optimization and larning-to-learn. CoRR \narXiv:1712.06283\n\n."},{"key":"5838_CR15","first-page":"4996","volume":"31","author":"V Garg","year":"2018","unstructured":"Garg, V. (2018). Supervising unsupervised learning. Advances in Neural Information Processing Systems, 31, 4996\u20135006.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5838_CR16","doi-asserted-by":"crossref","unstructured":"Gu, J., Wang, Y., Chen, Y., Li, V. O. K., & Cho, K. (2018). Meta-learning for low-resource neural machine translation. In Proceedings of the 2018 conference on empirical methods in natural language processing, Brussels, Belgium (pp. 3622\u20133631).","DOI":"10.18653\/v1\/D18-1398"},{"key":"5838_CR17","unstructured":"Hariharan, B., & Girshick, R. B. (2017). Low-shot visual recognition by shrinking and hallucinating features. In IEEE international conference on computer vision (pp. 3037\u20133046). Italy: Venice."},{"key":"5838_CR18","unstructured":"Hsu, K., Levine, S., & Finn, C. (2018). Unsupervised learning via meta-learning. CoRR \narXiv:1810.02334"},{"key":"5838_CR19","unstructured":"Huang, P. S., Wang, C., Singh, R., Yih, W., & He, X. (2018). Natural language to structured query generation via meta-learning. In Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics: Human language technologies, New Orleans, LA (pp. 732\u2013738)."},{"issue":"10","key":"5838_CR20","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1109\/TPAMI.2014.2307881","volume":"36","author":"SJ Huang","year":"2014","unstructured":"Huang, S. J., Jin, R., & Zhou, Z. H. (2014). Active learning by querying informative and representative examples. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(10), 1936\u20131949.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"5838_CR21","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd international conference on machine learning, Lille, France (pp. 448\u2013456)."},{"key":"5838_CR22","doi-asserted-by":"crossref","unstructured":"Karlinsky, L., Shtok, J., Tzur, Y., & Tzadok, A. (2017). Fine-grained recognition of thousands of object categories with single-example training. In IEEE conference on computer vision and pattern recognition, Honolulu, HI (pp. 965\u2013974).","DOI":"10.1109\/CVPR.2017.109"},{"key":"5838_CR23","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. CoRR \narXiv:1412.6980\n\n."},{"key":"5838_CR24","unstructured":"Koch, G., Zemel, R., & Salakhutdinov, R. (2015). Siamese neural networks for one-shot image recognition. In ICML deep learning workshop (Vol. 2) \nhttps:\/\/sites.google.com\/site\/deeplearning2015\/home\n\n."},{"issue":"6","key":"5838_CR25","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84\u201390.","journal-title":"Communications of the ACM"},{"key":"5838_CR26","unstructured":"Lake, B. M., Salakhutdinov, R., Gross, J., & Tenenbaum, J. B. (2011). One shot learning of simple visual concepts. In Proceedings of the 33th annual meeting of the cognitive science society, Boston, MA."},{"issue":"6266","key":"5838_CR27","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1126\/science.aab3050","volume":"350","author":"BM Lake","year":"2015","unstructured":"Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015). Human-level concept learning through probabilistic program induction. Science, 350(6266), 1332\u20131338.","journal-title":"Science"},{"key":"5838_CR28","unstructured":"Lee, Y., & Choi, S. (2018). Gradient-based meta-learning with learned layerwise metric and subspace. In Proceedings of the 35th international conference on machine learning, Stockholm, Sweden (pp. 2933\u20132942)."},{"issue":"4","key":"5838_CR29","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","volume":"28","author":"FF Li","year":"2006","unstructured":"Li, F. F., Fergus, R., & Perona, P. (2006). One-shot learning of object categories. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(4), 594\u2013611.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"5838_CR30","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1109\/TPAMI.2014.2299812","volume":"37","author":"YF Li","year":"2015","unstructured":"Li, Y. F., & Zhou, Z. H. (2015). Towards making unlabeled data never hurt. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(1), 175\u2013188.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"5838_CR31","unstructured":"Li, Z., Zhou, F., Chen, F., & Li, H. (2017). Meta-SGD: Learning to learn quickly for few shot learning. CoRR \narXiv:1707.09835\n\n."},{"issue":"3","key":"5838_CR32","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1007\/s10994-009-5109-7","volume":"75","author":"A Maurer","year":"2009","unstructured":"Maurer, A. (2009). Transfer bounds for linear feature learning. Machine Learning, 75(3), 327\u2013350.","journal-title":"Machine Learning"},{"key":"5838_CR33","first-page":"81:1","volume":"17","author":"A Maurer","year":"2016","unstructured":"Maurer, A., Pontil, M., & Romera-Paredes, B. (2016). The benefit of multitask representation learning. Journal of Machine Learning Research, 17, 81:1\u201381:32.","journal-title":"Journal of Machine Learning Research"},{"key":"5838_CR34","first-page":"6673","volume":"30","author":"S Motiian","year":"2017","unstructured":"Motiian, S., Jones, Q., Iranmanesh, S. M., & Doretto, G. (2017). Few-shot adversarial domain adaptation. Advances in Neural Information Processing Systems, 30, 6673\u20136683.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5838_CR35","unstructured":"Nichol, A., Achiam, J., & Schulman, J. (2018). On first-order meta-learning algorithms. CoRR \narXiv:1803.02999\n\n."},{"key":"5838_CR36","first-page":"53:1","volume":"20","author":"P Probst","year":"2019","unstructured":"Probst, P., Boulesteix, A. L., & Bischl, B. (2019). Tunability: Importance of hyperparameters of machine learning algorithms. Journal of Machine Learning Research, 20, 53:1\u201353:32.","journal-title":"Journal of Machine Learning Research"},{"key":"5838_CR37","unstructured":"Ravi, S., & Larochelle, H. (2017). Optimization as a model for few-shot learning. In In international conference on learning representations."},{"key":"5838_CR38","unstructured":"Reed, S. E., Chen, Y., Paine, T., van\u00a0den Oord, A., Eslami S. M. A., Rezende, D. J., Vinyals, O., & de\u00a0Freitas, N. (2017). Few-shot autoregressive density estimation: Towards learning to learn distributions. CoRR \narXiv:1710.10304\n\n."},{"key":"5838_CR39","unstructured":"Ren, M., Zeng, W., Yang, B., & Urtasun, R. (2018). Learning to reweight examples for robust deep learning. In Proceedings of the 35th international conference on machine learning, Stockholm, Sweden (pp. 4331\u20134340)."},{"issue":"3","key":"5838_CR40","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"5838_CR41","unstructured":"Rusu, A. A., Rao, D., Sygnowski, J., Vinyals, O., Pascanu, R., Osindero, S., & Hadsell, R. (2018). Meta-learning with latent embedding optimization. CoRR \narXiv:1807.05960\n\n."},{"key":"5838_CR42","unstructured":"Shyam, P., Gupta, S., & Dukkipati, A. (2017). Attentive recurrent comparators. In Proceedings of the 34th international conference on machine learning, Sydney, Australia (pp. 3173\u20133181)."},{"key":"5838_CR43","first-page":"4080","volume":"30","author":"J Snell","year":"2017","unstructured":"Snell, J., Swersky, K., & Zemel, R. S. (2017). Prototypical networks for few-shot learning. Advances in Neural Information Processing Systems, 30, 4080\u20134090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5838_CR44","doi-asserted-by":"crossref","unstructured":"Su, D., Zhang, H., Chen, H., Yi, J., Chen, P. Y., & Gao, Y. (2018). Is robustness the cost of accuracy? A comprehensive study on the robustness of 18 deep image classification models. In Proceedings of the 15th European conference on computer vision, Munich, Germany (pp. 644\u2013661).","DOI":"10.1007\/978-3-030-01258-8_39"},{"key":"5838_CR45","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P. H. S., & Hospedales, T. M. (2017). Learning to compare: Relation network for few-shot learning. CoRR \narXiv:1711.06025\n\n."},{"issue":"9","key":"5838_CR46","doi-asserted-by":"publisher","first-page":"1725","DOI":"10.1016\/j.patcog.2006.03.013","volume":"39","author":"X Tan","year":"2006","unstructured":"Tan, X., Chen, S., Zhou, Z. H., & Zhang, F. (2006). Face recognition from a single image per person: A survey. Pattern Recognition, 39(9), 1725\u20131745.","journal-title":"Pattern Recognition"},{"key":"5838_CR47","volume-title":"Learning to learn","author":"S Thrun","year":"2012","unstructured":"Thrun, S., & Pratt, L. (2012). Learning to learn. New York: Springer."},{"key":"5838_CR48","first-page":"2252","volume":"30","author":"E Triantafillou","year":"2017","unstructured":"Triantafillou, E., Zemel, R. S., & Urtasun, R. (2017). Few-shot learning through an information retrieval lens. Advances in Neural Information Processing Systems, 30, 2252\u20132262.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5838_CR49","unstructured":"Triantafillou, E., Zhu, T., Dumoulin, V., Lamblin, P., Xu, K., Goroshin, R., Gelada, C., Swersky, K., Manzagol, P. A., & Larochelle, H. (2019). Meta-dataset: A dataset of datasets for learning to learn from few examples. CoRR \narXiv:1903.03096\n\n."},{"key":"5838_CR50","first-page":"6907","volume":"30","author":"M Vartak","year":"2017","unstructured":"Vartak, M., Thiagarajan, A., Miranda, C., Bratman, J., & Larochelle, H. (2017). A meta-learning perspective on cold-start recommendations for items. Advances in Neural Information Processing Systems, 30, 6907\u20136917.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5838_CR51","first-page":"6000","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., et al. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 6000\u20136010.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"5838_CR52","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1023\/A:1019956318069","volume":"18","author":"R Vilalta","year":"2002","unstructured":"Vilalta, R., & Drissi, Y. (2002). A perspective view and survey of meta-learning. Artificial Intelligence Review, 18(2), 77\u201395.","journal-title":"Artificial Intelligence Review"},{"key":"5838_CR53","first-page":"3630","volume":"29","author":"O Vinyals","year":"2016","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., & Wierstra, D. (2016). Matching networks for one shot learning. Advances in Neural Information Processing Systems, 29, 3630\u20133638.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5838_CR54","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., & Belongie, S. (2011). The Caltech-UCSD birds-200-2011 dataset. Technical report."},{"key":"5838_CR55","doi-asserted-by":"crossref","unstructured":"Wang, P., Liu, L., Shen, C., Huang, Z., van\u00a0den Hengel, A., & Shen, H.T. (2017a). Multi-attention network for one shot learning. In IEEE conference on computer vision and pattern recognition, Honolulu, HI (pp. 6212\u20136220).","DOI":"10.1109\/CVPR.2017.658"},{"key":"5838_CR56","unstructured":"Wang, T., Zhu, J. Y., Torralba, A., & Efros, A. A. (2018a). Dataset distillation. CoRR \narXiv:1811.10959\n\n."},{"key":"5838_CR57","first-page":"7032","volume":"30","author":"Y Wang","year":"2017","unstructured":"Wang, Y., Ramanan, D., & Hebert, M. (2017b). Learning to model the tail. Advances in Neural Information Processing Systems, 30, 7032\u20137042.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5838_CR58","doi-asserted-by":"crossref","unstructured":"Wang, Y., Girshick, R. B., Hebert, M., & Hariharan, B. (2018b). Low-shot learning from imaginary data. CoRR \narXiv:1801.05401\n\n.","DOI":"10.1109\/CVPR.2018.00760"},{"key":"5838_CR59","unstructured":"Ye, H. J., Hu, H., Zhan, D. C., & Sha, F. (2018). Learning embedding adaptation for few-shot learning. CoRR \narXiv:1812.03664\n\n."},{"key":"5838_CR60","unstructured":"Yu, T., Finn, C., Xie, A., Dasari, S., Zhang, T., Abbeel, P., & Levine, S. (2018). One-shot imitation from observing humans via domain-adaptive meta-learning. CoRR \narXiv:1802.01557\n\n."},{"key":"5838_CR61","first-page":"3394","volume":"30","author":"M Zaheer","year":"2017","unstructured":"Zaheer, M., Kottur, S., Ravanbakhsh, S., P\u00f3czos, B., Salakhutdinov, R. R., & Smola, A. J. (2017). Deep sets. Advances in Neural Information Processing Systems, 30, 3394\u20133404.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5838_CR62","first-page":"5776","volume":"31","author":"Y Zhang","year":"2018","unstructured":"Zhang, Y., Wei, Y., & Yang, Q. (2018). Learning to multitask. Advances in Neural Information Processing Systems, 31, 5776\u20135787.","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-019-05838-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-019-05838-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-019-05838-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,10]],"date-time":"2020-10-10T00:03:53Z","timestamp":1602288233000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-019-05838-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,10]]},"references-count":62,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["5838"],"URL":"https:\/\/doi.org\/10.1007\/s10994-019-05838-7","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2019,10,10]]},"assertion":[{"value":"4 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}