Skip Abstract Section
Abstract
Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction. Moreover, deep learning is notorious for poor generalization from few samples. Meta-learning is a promising approach that addresses these issues by adapting to new tasks with few-shot datasets. This survey first briefly introduces meta-learning and then investigates state-of-the-art meta-learning methods and recent advances in: (i) metric-based, (ii) memory-based, (iii), and learning-based methods. Finally, current challenges and insights for future researches are discussed.
- Mounir Abdelaziz and Zuping Zhang. 2022. Multi-scale kronecker-product relation networks for few-shot learning. Multimedia Tools and Applications 81, 5 (2022), 6703–6722.Google Scholar
Digital Library
- Dalal A Alajaji and Haikel Alhichri. 2020. Few shot scene classification in remote sensing using meta-agnostic machine. In 2020 6th conference on data science and machine learning applications (CDMA). IEEE, 77–80.Google ScholarCross Ref
- Sajid Ali, Tamer Abuhmed, Shaker El-Sappagh, Khan Muhammad, Jose M Alonso-Moral, Roberto Confalonieri, Riccardo Guidotti, Javier Del Ser, Natalia Díaz-Rodríguez, and Francisco Herrera. 2023. Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence. Information Fusion 99(2023), 101805.Google ScholarDigital Library
- Md Rabiul Awal, Roy Ka-Wei Lee, Eshaan Tanwar, Tanmay Garg, and Tanmoy Chakraborty. 2023. Model-agnostic meta-learning for multilingual hate speech detection. IEEE Transactions on Computational Social Systems (2023).Google Scholar
- Sungyong Baik, Seokil Hong, and Kyoung Mu Lee. 2020. Learning to forget for meta-learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2379–2387.Google ScholarCross Ref
- Pierre Baldi and Yves Chauvin. 1993. Neural networks for fingerprint recognition. neural computation 5, 3 (1993), 402–418.Google Scholar
- Atilim Gunes Baydin, Robert Cornish, David Martinez Rubio, Mark Schmidt, and Frank Wood. 2017. Online learning rate adaptation with hypergradient descent. arXiv preprint arXiv:1703.04782(2017).Google Scholar
- Harkirat Singh Behl, Atılım Güneş Baydin, and Philip HS Torr. 2019. Alpha maml: Adaptive model-agnostic meta-learning. arXiv preprint arXiv:1905.07435(2019).Google Scholar
- Luca Bertinetto, Joao F Henriques, Philip Torr, and Andrea Vedaldi. 2018. Meta-learning with differentiable closed-form solvers. In International Conference on Learning Representations.Google Scholar
- Luca Bertinetto, João F Henriques, Jack Valmadre, Philip Torr, and Andrea Vedaldi. 2016. Learning feed-forward one-shot learners. Advances in neural information processing systems 29 (2016).Google Scholar
- Hemanthage S Bhathiya and Uthayasanker Thayasivam. 2020. Meta learning for few-shot joint intent detection and slot-filling. In Proceedings of the 2020 5th International Conference on Machine Learning Technologies. 86–92.Google ScholarDigital Library
- Jane Bromley, Isabelle Guyon, Yann LeCun, Eduard Säckinger, and Roopak Shah. 1993. Signature verification using a” siamese” time delay neural network. Advances in neural information processing systems 6 (1993).Google Scholar
- Mengting Chen, Xinggang Wang, Heng Luo, Yifeng Geng, and Wenyu Liu. 2021. Learning to focus: cascaded feature matching network for few-shot image recognition. Science China Information Sciences 64, 9 (2021), 1–13.Google ScholarCross Ref
- Xi Chen, Ali Ghadirzadeh, Mårten Björkman, and Patric Jensfelt. 2019. Meta-learning for multi-objective reinforcement learning. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 977–983.Google ScholarDigital Library
- Davide Chicco. 2021. Siamese neural networks: An overview. Artificial Neural Networks(2021), 73–94.Google Scholar
- Sumit Chopra, Raia Hadsell, and Yann LeCun. 2005. Learning a similarity metric discriminatively, with application to face verification. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), Vol. 1. IEEE, 539–546.Google ScholarDigital Library
- Jessica Deuschel, Daniel Firmbach, Carol I Geppert, Markus Eckstein, Arndt Hartmann, Volker Bruns, Petr Kuritcyn, Jakob Dexl, David Hartmann, Dominik Perrin, et al. 2021. Multi-Prototype Few-shot Learning in Histopathology. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 620–628.Google ScholarCross Ref
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018).Google Scholar
- Yueming Ding, Xia Tian, Lirong Yin, Xiaobing Chen, Shan Liu, Bo Yang, and Wenfeng Zheng. 2019. Multi-scale relation network for few-shot learning based on meta-learning. In International Conference on Computer Vision Systems. Springer, 343–352.Google ScholarCross Ref
- Harrison Edwards and Amos Storkey. 2016. Towards a neural statistician. arXiv preprint arXiv:1606.02185(2016).Google Scholar
- Abolfazl Farahani, Sahar Voghoei, Khaled Rasheed, and Hamid R Arabnia. 2021. A brief review of domain adaptation. Advances in data science and information engineering (2021), 877–894.Google Scholar
- Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning. PMLR, 1126–1135.Google Scholar
- Chelsea Finn and Sergey Levine. 2018. Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm. In International Conference on Learning Representations.Google Scholar
- Chelsea Finn, Kelvin Xu, and Sergey Levine. 2018. Probabilistic model-agnostic meta-learning. Advances in neural information processing systems 31 (2018).Google Scholar
- Chelsea B Finn. 2018. Learning to learn with gradients. University of California, Berkeley.Google Scholar
- Stanislav Fort. 2017. Gaussian prototypical networks for few-shot learning on omniglot. arXiv preprint arXiv:1708.02735(2017).Google Scholar
- Victor Garcia and Joan Bruna. 2017. Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043(2017).Google Scholar
- Victor Garcia and Joan Bruna. 2018. Few-shot learning with graph neural networks. In 6th International Conference on Learning Representations, ICLR 2018.Google Scholar
- Marta Garnelo, Dan Rosenbaum, Christopher Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo Rezende, and SM Ali Eslami. 2018. Conditional neural processes. In International Conference on Machine Learning. PMLR, 1704–1713.Google Scholar
- Spyros Gidaris and Nikos Komodakis. 2018. Dynamic few-shot visual learning without forgetting. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4367–4375.Google ScholarCross Ref
- Spyros Gidaris and Nikos Komodakis. 2019. Generating classification weights with gnn denoising autoencoders for few-shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 21–30.Google ScholarCross Ref
- Micah Goldblum, Liam Fowl, and Tom Goldstein. 2020. Adversarially robust few-shot learning: A meta-learning approach. Advances in Neural Information Processing Systems 33 (2020), 17886–17895.Google Scholar
- Erin Grant, Chelsea Finn, Sergey Levine, Trevor Darrell, and Thomas Griffiths. 2018. Recasting gradient-based meta-learning as hierarchical bayes. arXiv preprint arXiv:1801.08930(2018).Google Scholar
- Alex Graves, Greg Wayne, and Ivo Danihelka. 2014. Neural turing machines. arXiv preprint arXiv:1410.5401(2014).Google Scholar
- Jiatao Gu, Yong Wang, Yun Chen, Kyunghyun Cho, and Victor OK Li. 2018. Meta-learning for low-resource neural machine translation. arXiv preprint arXiv:1808.08437(2018).Google Scholar
- Chengcheng Han, Zeqiu Fan, Dongxiang Zhang, Minghui Qiu, Ming Gao, and Aoying Zhou. 2021. Meta-learning adversarial domain adaptation network for few-shot text classification. arXiv preprint arXiv:2107.12262(2021).Google Scholar
- Chengcheng Han, Yuhe Wang, Yingnan Fu, Xiang Li, Minghui Qiu, Ming Gao, and Aoying Zhou. 2023. Meta-learning Siamese Network for Few-Shot Text Classification. In International Conference on Database Systems for Advanced Applications. Springer, 737–752.Google Scholar
- Mengya Han, Ronggui Wang, Juan Yang, Lixia Xue, and Min Hu. 2020. Multi-scale feature network for few-shot learning. Multimedia Tools and Applications 79, 17 (2020), 11617–11637.Google ScholarDigital Library
- Jun He, Richang Hong, Xueliang Liu, Mingliang Xu, Zheng-Jun Zha, and Meng Wang. 2020. Memory-augmented relation network for few-shot learning. In Proceedings of the 28th ACM International Conference on Multimedia. 1236–1244.Google ScholarDigital Library
- Nathan Hilliard, Lawrence Phillips, Scott Howland, Artëm Yankov, Courtney D Corley, and Nathan O Hodas. 2018. Few-shot learning with metric-agnostic conditional embeddings. arXiv preprint arXiv:1802.04376(2018).Google Scholar
- Yufan Hu, Junyu Gao, and Changsheng Xu. 2020. Learning dual-pooling graph neural networks for few-shot video classification. IEEE Transactions on Multimedia 23 (2020), 4285–4296.Google ScholarCross Ref
- Hongwei Huang, Zhangkai Wu, Wenbin Li, Jing Huo, and Yang Gao. 2021. Local descriptor-based multi-prototype network for few-shot learning. Pattern Recognition 116(2021), 107935.Google ScholarDigital Library
- Kuan-Po Huang, Yuan-Kuei Wu, and Hung-yi Lee. 2021. Multi-accent speech separation with one shot learning. arXiv preprint arXiv:2106.11713(2021).Google Scholar
- Mike Huisman, Jan N Van Rijn, and Aske Plaat. 2021. A survey of deep meta-learning. Artificial Intelligence Review 54, 6 (2021), 4483–4541.Google ScholarDigital Library
- Olga Ilina, Vadim Ziyadinov, Nikolay Klenov, and Maxim Tereshonok. 2022. A Survey on Symmetrical Neural Network Architectures and Applications. Symmetry 14, 7 (2022), 1391.Google ScholarCross Ref
- Muhammad Abdullah Jamal and Guo-Jun Qi. 2019. Task agnostic meta-learning for few-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11719–11727.Google ScholarCross Ref
- Zhong Ji, Xingliang Chai, Yunlong Yu, Yanwei Pang, and Zhongfei Zhang. 2020. Improved prototypical networks for few-shot learning. Pattern Recognition Letters 140 (2020), 81–87.Google ScholarDigital Library
- Hongyang Jiang, Mengdi Gao, Heng Li, Richu Jin, Hanpei Miao, and Jiang Liu. 2022. Multi-Learner Based Deep Meta-Learning for Few-Shot Medical Image Classification. IEEE Journal of Biomedical and Health Informatics 27, 1(2022), 17–28.Google ScholarCross Ref
- Xiang Jiang, Mohammad Havaei, Gabriel Chartrand, Hassan Chouaib, Thomas Vincent, Andrew Jesson, Nicolas Chapados, and Stan Matwin. 2018. Attentive task-agnostic meta-learning for few-shot text classification. (2018).Google Scholar
- Ilchae Jung, Kihyun You, Hyeonwoo Noh, Minsu Cho, and Bohyung Han. 2020. Real-time object tracking via meta-learning: Efficient model adaptation and one-shot channel pruning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 11205–11212.Google ScholarCross Ref
- Rituraj Kaushik, Timothée Anne, and Jean-Baptiste Mouret. 2020. Fast online adaptation in robotics through meta-learning embeddings of simulated priors. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 5269–5276.Google ScholarDigital Library
- Kian Kenyon-Dean, Andre Cianflone, Lucas Page-Caccia, Guillaume Rabusseau, Jackie Chi Kit Cheung, and Doina Precup. 2018. Clustering-oriented representation learning with attractive-repulsive loss. arXiv preprint arXiv:1812.07627(2018).Google Scholar
- Rabindra Khadka, Debesh Jha, Steven Hicks, Vajira Thambawita, Michael A Riegler, Sharib Ali, and Pål Halvorsen. 2022. Meta-learning with implicit gradients in a few-shot setting for medical image segmentation. Computers in Biology and Medicine 143 (2022), 105227.Google ScholarDigital Library
- Byeonggeun Kim, Seunghan Yang, Inseop Chung, and Simyung Chang. 2022. Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting. arXiv preprint arXiv:2206.13691(2022).Google Scholar
- Gregory Koch, Richard Zemel, Ruslan Salakhutdinov, et al. 2015. Siamese neural networks for one-shot image recognition. In ICML deep learning workshop, Vol. 2. Lille, 0.Google Scholar
- Steinar Laenen and Luca Bertinetto. 2021. On episodes, prototypical networks, and few-shot learning. Advances in Neural Information Processing Systems 34 (2021), 24581–24592.Google Scholar
- Brenden Lake, Ruslan Salakhutdinov, Jason Gross, and Joshua Tenenbaum. 2011. One shot learning of simple visual concepts. In Proceedings of the annual meeting of the cognitive science society, Vol. 33.Google Scholar
- Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran, and Stefano Soatto. 2019. Meta-learning with differentiable convex optimization. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10657–10665.Google ScholarCross Ref
- Aoxue Li, Tiange Luo, Tao Xiang, Weiran Huang, and Liwei Wang. 2019. Few-shot learning with global class representations. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 9715–9724.Google ScholarCross Ref
- Haifeng Li, Zhenqi Cui, Zhiqing Zhu, Li Chen, Jiawei Zhu, Haozhe Huang, and Chao Tao. 2020. RS-MetaNet: Deep meta metric learning for few-shot remote sensing scene classification. arXiv preprint arXiv:2009.13364(2020).Google Scholar
- Huaiyu Li, Weiming Dong, Xing Mei, Chongyang Ma, Feiyue Huang, and Bao-Gang Hu. 2019. LGM-Net: Learning to generate matching networks for few-shot learning. In International conference on machine learning. PMLR, 3825–3834.Google Scholar
- Xiaoxu Li, Zhuo Sun, Jing-Hao Xue, and Zhanyu Ma. 2021. A concise review of recent few-shot meta-learning methods. Neurocomputing 456(2021), 463–468.Google ScholarDigital Library
- Yong Li, Zhenfeng Shao, Xiao Huang, Bowen Cai, and Song Peng. 2021. Meta-FSEO: A meta-learning fast adaptation with self-supervised embedding optimization for few-shot remote sensing scene classification. Remote Sensing 13, 14 (2021), 2776.Google ScholarCross Ref
- Zhenguo Li, Fengwei Zhou, Fei Chen, and Hang Li. 2017. Meta-sgd: Learning to learn quickly for few-shot learning. arXiv preprint arXiv:1707.09835(2017).Google Scholar
- Bin Liang, Xiang Li, Lin Gui, Yonghao Fu, Yulan He, Min Yang, and Ruifeng Xu. 2023. Few-shot aspect category sentiment analysis via meta-learning. ACM Transactions on Information Systems 41, 1 (2023), 1–31.Google ScholarDigital Library
- Bo Liu, Hao Kang, Haoxiang Li, Gang Hua, and Nuno Vasconcelos. 2020. Few-shot open-set recognition using meta-learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8798–8807.Google ScholarCross Ref
- Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Junjie Sun, Hong Yu, and Xianchao Zhang. 2022. Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1079–1087.Google ScholarDigital Library
- Shuai Liu, Shichen Huang, Shuai Wang, Khan Muhammad, Paolo Bellavista, and Javier Del Ser. 2023. Visual tracking in complex scenes: A location fusion mechanism based on the combination of multiple visual cognition flows. Information Fusion 96(2023), 281–296.Google ScholarDigital Library
- Xiaoqian Liu, Fengyu Zhou, Jin Liu, and Lianjie Jiang. 2020. Meta-learning based prototype-relation network for few-shot classification. Neurocomputing 383(2020), 224–234.Google ScholarDigital Library
- Jiang Lu, Zhong Cao, Kailun Wu, Gang Zhang, and Changshui Zhang. 2018. Boosting few-shot image recognition via domain alignment prototypical networks. In 2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 260–264.Google ScholarCross Ref
- Jiang Lu, Pinghua Gong, Jieping Ye, and Changshui Zhang. 2020. Learning from very few samples: A survey. arXiv preprint arXiv:2009.02653(2020).Google Scholar
- Liangfu Lu, Xudong Cui, Zhiyuan Tan, and Yulei Wu. 2023. MedOptNet: Meta-Learning Framework for Few-shot Medical Image Classification. IEEE/ACM Transactions on Computational Biology and Bioinformatics (2023).Google Scholar
- Shuai Luo, Yujie Li, Pengxiang Gao, Yichuan Wang, and Seiichi Serikawa. 2022. Meta-seg: A survey of meta-learning for image segmentation. Pattern Recognition 126(2022), 108586.Google ScholarDigital Library
- Sijie Mai, Haifeng Hu, and Jia Xu. 2019. Attentive matching network for few-shot learning. Computer Vision and Image Understanding 187 (2019), 102781.Google ScholarDigital Library
- Iaroslav Melekhov, Juho Kannala, and Esa Rahtu. 2016. Siamese network features for image matching. In 2016 23rd international conference on pattern recognition (ICPR). IEEE, 378–383.Google ScholarCross Ref
- Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, and Pieter Abbeel. 2017. A simple neural attentive meta-learner. arXiv preprint arXiv:1707.03141(2017).Google Scholar
- Tom M Mitchell and Tom M Mitchell. 1997. Machine learning. Vol. 1. McGraw-hill New York.Google Scholar
- Marzieh Mozafari, Reza Farahbakhsh, and Noel Crespi. 2022. Cross-lingual few-shot hate speech and offensive language detection using meta learning. IEEE Access 10(2022), 14880–14896.Google ScholarCross Ref
- Tsendsuren Munkhdalai and Hong Yu. 2017. Meta networks. In International Conference on Machine Learning. PMLR, 2554–2563.Google Scholar
- Alex Nichol, Joshua Achiam, and John Schulman. 2018. On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999(2018).Google Scholar
- Jaehoon Oh, Hyungjun Yoo, ChangHwan Kim, and Se-Young Yun. 2020. BOIL: Towards representation change for few-shot learning. arXiv preprint arXiv:2008.08882(2020).Google Scholar
- Frederik Pahde, Mihai Puscas, Tassilo Klein, and Moin Nabi. 2021. Multimodal prototypical networks for few-shot learning. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2644–2653.Google ScholarCross Ref
- Sinno Jialin Pan and Qiang Yang. 2009. A survey on transfer learning. IEEE Transactions on knowledge and data engineering 22, 10(2009), 1345–1359.Google ScholarDigital Library
- Yingwei Pan, Ting Yao, Yehao Li, Yu Wang, Chong-Wah Ngo, and Tao Mei. 2019. Transferrable prototypical networks for unsupervised domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2239–2247.Google ScholarCross Ref
- Sumit Pandey and Srishti Sharma. 2023. Meta-Learned Word Embeddings for Few-Shot Sentiment Classification. In International Conference on Smart Trends in Computing and Communications. Springer, 577–589.Google Scholar
- Hang Qi, Matthew Brown, and David G Lowe. 2018. Low-shot learning with imprinted weights. In Proceedings of the IEEE conference on computer vision and pattern recognition. 5822–5830.Google ScholarCross Ref
- Aravind Rajeswaran, Chelsea Finn, Sham M Kakade, and Sergey Levine. 2019. Meta-learning with implicit gradients. Advances in neural information processing systems 32 (2019).Google Scholar
- Sachin Ravi and Hugo Larochelle. 2016. Optimization as a model for few-shot learning. (2016).Google Scholar
- Li Ren, Guiduo Duan, Tianxi Huang, and Zhao Kang. 2022. Multi-local feature relation network for few-shot learning. Neural Computing and Applications 34, 10 (2022), 7393–7403.Google ScholarDigital Library
- Mengye Ren, Renjie Liao, Ethan Fetaya, and Richard Zemel. 2019. Incremental few-shot learning with attention attractor networks. Advances in Neural Information Processing Systems 32 (2019).Google Scholar
- Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B Tenenbaum, Hugo Larochelle, and Richard S Zemel. 2018. Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676(2018).Google Scholar
- Sebastian Ruder, Matthew E Peters, Swabha Swayamdipta, and Thomas Wolf. 2019. Transfer learning in natural language processing. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: Tutorials. 15–18.Google ScholarCross Ref
- Andrei A Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, and Raia Hadsell. 2018. Meta-learning with latent embedding optimization. arXiv preprint arXiv:1807.05960(2018).Google Scholar
- Alok Ranjan Sahoo and Pavan Chakraborty. 2022. A Study on Position Control of a Continuum Arm Using MAML (Model-Agnostic Meta-Learning) for Adapting Different Loading Conditions. IEEE Access 10(2022), 14980–14992.Google ScholarCross Ref
- Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, and Timothy Lillicrap. 2016. Meta-learning with memory-augmented neural networks. In International conference on machine learning. PMLR, 1842–1850.Google Scholar
- Adam Santoro, David Raposo, David G Barrett, Mateusz Malinowski, Razvan Pascanu, Peter Battaglia, and Timothy Lillicrap. 2017. A simple neural network module for relational reasoning. Advances in neural information processing systems 30 (2017).Google Scholar
- Manali Shaha and Meenakshi Pawar. 2018. Transfer learning for image classification. In 2018 second international conference on electronics, communication and aerospace technology (ICECA). IEEE, 656–660.Google Scholar
- Amr Sharaf, Hany Hassan, and Hal Daumé III. 2020. Meta-learning for few-shot NMT adaptation. arXiv preprint arXiv:2004.02745(2020).Google Scholar
- Pranav Shyam, Shubham Gupta, and Ambedkar Dukkipati. 2017. Attentive recurrent comparators. In International conference on machine learning. PMLR, 3173–3181.Google Scholar
- Satwinder Singh, Ruili Wang, and Feng Hou. 2022. Improved meta learning for low resource speech recognition. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 4798–4802.Google ScholarCross Ref
- Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems 30 (2017).Google Scholar
- Qianru Sun, Yaoyao Liu, Tat-Seng Chua, and Bernt Schiele. 2019. Meta-transfer learning for few-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 403–412.Google ScholarCross Ref
- Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip HS Torr, and Timothy M Hospedales. 2018. Learning to compare: Relation network for few-shot learning. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1199–1208.Google ScholarCross Ref
- Xu Tang, Weiquan Lin, Chao Liu, Xiao Han, Wenjing Wang, Jingjing Ma, and Licheng Jiao. 2021. Multi-Scale Meta-Learning-Based Networks for High-Resolution Remote Sensing Scene Classification. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE, 4928–4931.Google Scholar
- Sebastian Thrun and Lorien Pratt. 2012. Learning to learn. Springer Science & Business Media.Google Scholar
- Kien Tran, Hiroshi Sato, and Masao Kubo. 2019. Memory augmented matching networks for few-shot learnings. International Journal of Machine Learning and Computing 9, 6 (2019).Google ScholarCross Ref
- Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Utku Evci, Kelvin Xu, Ross Goroshin, Carles Gelada, Kevin Swersky, Pierre-Antoine Manzagol, et al. 2019. Meta-dataset: A dataset of datasets for learning to learn from few examples. arXiv preprint arXiv:1903.03096(2019).Google Scholar
- Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Daan Wierstra, et al. 2016. Matching networks for one shot learning. Advances in neural information processing systems 29 (2016).Google Scholar
- Catherine Wah, Steve Branson, Peter Welinder, Pietro Perona, and Serge Belongie. 2011. The caltech-ucsd birds-200-2011 dataset. (2011).Google Scholar
- Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell. 2020. Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726(2020).Google Scholar
- Guangting Wang, Chong Luo, Xiaoyan Sun, Zhiwei Xiong, and Wenjun Zeng. 2020. Tracking by instance detection: A meta-learning approach. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 6288–6297.Google ScholarCross Ref
- Jindong Wang, Cuiling Lan, Chang Liu, Yidong Ouyang, Tao Qin, Wang Lu, Yiqiang Chen, Wenjun Zeng, and Philip Yu. 2022. Generalizing to unseen domains: A survey on domain generalization. IEEE Transactions on Knowledge and Data Engineering (2022).Google Scholar
- Jane X Wang. 2021. Meta-learning in natural and artificial intelligence. Current Opinion in Behavioral Sciences 38 (2021), 90–95.Google ScholarCross Ref
- Mei Wang and Weihong Deng. 2018. Deep visual domain adaptation: A survey. Neurocomputing 312(2018), 135–153.Google ScholarDigital Library
- Xin Wang, Fisher Yu, Ruth Wang, Trevor Darrell, and Joseph E Gonzalez. 2019. Tafe-net: Task-aware feature embeddings for low shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 1831–1840.Google ScholarCross Ref
- Yu-Xiong Wang, Deva Ramanan, and Martial Hebert. 2019. Meta-learning to detect rare objects. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 9925–9934.Google ScholarCross Ref
- Xiu-Shen Wei, Jian-Hao Luo, Jianxin Wu, and Zhi-Hua Zhou. 2017. Selective convolutional descriptor aggregation for fine-grained image retrieval. IEEE Transactions on Image Processing 26, 6 (2017), 2868–2881.Google ScholarDigital Library
- Xiongwei Wu, Doyen Sahoo, and Steven Hoi. 2020. Meta-rcnn: Meta learning for few-shot object detection. In Proceedings of the 28th ACM International Conference on Multimedia. 1679–1687.Google ScholarDigital Library
- Zhiyu Xue, Lixin Duan, Wen Li, Lin Chen, and Jiebo Luo. 2020. Region comparison network for interpretable few-shot image classification. arXiv preprint arXiv:2009.03558(2020).Google Scholar
- Zhiyu Xue, Zhenshan Xie, Zheng Xing, and Lixin Duan. 2020. Relative position and map networks in few-shot learning for image classification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops. 932–933.Google ScholarCross Ref
- Chengxiang Yin, Jian Tang, Zhiyuan Xu, and Yanzhi Wang. 2018. Adversarial meta-learning. arXiv preprint arXiv:1806.03316(2018).Google Scholar
- Jaesik Yoon, Taesup Kim, Ousmane Dia, Sungwoong Kim, Yoshua Bengio, and Sungjin Ahn. 2018. Bayesian model-agnostic meta-learning. Advances in neural information processing systems 31 (2018).Google Scholar
- Jason Yosinski, Jeff Clune, Yoshua Bengio, and Hod Lipson. 2014. How transferable are features in deep neural networks?Advances in neural information processing systems 27 (2014).Google Scholar
- Kenny Young, Baoxiang Wang, and Matthew E Taylor. 2018. Metatrace actor-critic: Online step-size tuning by meta-gradient descent for reinforcement learning control. arXiv preprint arXiv:1805.04514(2018).Google Scholar
- Zhou Yu, Jun Yu, Chenchao Xiang, Jianping Fan, and Dacheng Tao. 2018. Beyond bilinear: Generalized multimodal factorized high-order pooling for visual question answering. IEEE transactions on neural networks and learning systems 29, 12(2018), 5947–5959.Google Scholar
- Lingling Zhang, Jun Liu, Minnan Luo, Xiaojun Chang, Qinghua Zheng, and Alexander G Hauptmann. 2019. Scheduled sampling for one-shot learning via matching network. Pattern Recognition 96(2019), 106962.Google ScholarDigital Library
- Pei Zhang, Yunpeng Bai, Dong Wang, Bendu Bai, and Ying Li. 2020. Few-shot classification of aerial scene images via meta-learning. Remote Sensing 13, 1 (2020), 108.Google ScholarCross Ref
- Pei Zhang, Yunpeng Bai, Dong Wang, Bendu Bai, and Ying Li. 2021. A meta-learning framework for few-shot classification of remote sensing scene. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 4590–4594.Google ScholarCross Ref
- Yaohui Zhu, Chenlong Liu, and Shuqiang Jiang. 2020. Multi-attention Meta Learning for Few-shot Fine-grained Image Recognition.. In IJCAI. 1090–1096.Google Scholar
- Zhenxi Zhu, Limin Wang, Sheng Guo, and Gangshan Wu. 2021. A closer look at few-shot video classification: A new baseline and benchmark. arXiv preprint arXiv:2110.12358(2021).Google Scholar
- Luisa M Zintgraf, Kyriacos Shiarlis, Vitaly Kurin, Katja Hofmann, and Shimon Whiteson. 2018. Caml: Fast context adaptation via meta-learning. (2018).Google Scholar
Index Terms
- Meta-learning approaches for few-shot learning: A survey of recent advances
Recommendations
A survey of deep meta-learning
AbstractDeep neural networks can achieve great successes when presented with large data sets and sufficient computational resources. However, their ability to learn new concepts quickly is limited. Meta-learning is one approach to address this issue, by ...
Can we improve meta-learning model in few-shot learning by aligning data distributions?
AbstractMeta-learning becomes a promising way to solve the few-shot learning problem in recent research. This paradigm mainly relies on hierarchical architecture and episodic training to achieve good generalization on the new learning task. ...
Imbalanced Few-Shot Learning Based on Meta-transfer Learning
Artificial Neural Networks and Machine Learning – ICANN 2023AbstractFew-shot learning is a challenging task that aims to learn to adapt to new tasks with only a few labeled samples. Meta-learning is a promising approach to address this challenge, but the learned meta-knowledge on training sets may not always be ...
Comments