Affiliation:
1. East China Normal University, China
2. Michigan State University, United States
3. Macau University of Science and Technology, China
4. Siksha “O” Anusandhan University, India
Abstract
Few-shot learning (FSL) has emerged as an effective learning method and shows great potential. Despite the recent creative works in tackling FSL tasks, learning valid information rapidly from just a few or even zero samples remains a serious challenge. In this context, we extensively investigated 200+ FSL papers published in top journals and conferences in the past three years, aiming to present a timely and comprehensive overview of the most recent advances in FSL with a fresh perspective and to provide an impartial comparison of the strengths and weaknesses of existing work. To avoid conceptual confusion, we first elaborate and contrast a set of relevant concepts including few-shot learning, transfer learning, and meta-learning. Then, we inventively extract prior knowledge related to few-shot learning in the form of a pyramid, which summarizes and classifies previous work in detail from the perspective of challenges. Furthermore, to enrich this survey, we present in-depth analysis and insightful discussions of recent advances in each subsection. What is more, taking computer vision as an example, we highlight the important application of FSL, covering various research hotspots. Finally, we conclude the survey with unique insights into technology trends and potential future research opportunities to guide FSL follow-up research.
Funder
National Key R&D Program of China
Publisher
Association for Computing Machinery (ACM)
Subject
General Computer Science,Theoretical Computer Science
Reference268 articles.
1. Wenbo Zheng, Lan Yan, Chao Gou, and Fei-Yue Wang. 2021. Federated meta-learning for fraudulent credit card detection. In Proceedings of the 29th International Conference on International Joint Conference on Artificial Intelligence. 4654–4660.
2. Adrian El Baz, Ihsan Ullah, et al. 2022. Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification. In NeurIPS 2021 Competitions and Demonstrations Track. PMLR, 80–96.
3. FewJoint: Few-shot learning for joint dialogue understanding;Hou Yutai;Int. J. Mach. Learn. Cyber.,2022
4. MFNP: A Meta-optimized Model for Few-shot Next POI Recommendation
5. Few-Shot Learning for Decoding Surface Electromyography for Hand Gesture Recognition
Cited by
113 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献