Generalizing from a Few Examples: A Survey on Few-Shot Learning

  • 类型:arxiv
  • 标识:1904.05046
  • 链接:https://arxiv.org/abs/1904.05046
  • 主题:rag
  • 主分类:engineering
  • 形态:survey
  • 被引:2185
  • 被引来源:Semantic Scholar
  • S2被引:2185
  • OpenAlex被引:802
  • 影响力被引:58
  • TLDR:A thorough survey to fully understand Few-shot Learning and categorize FSL methods from three perspectives: data, which uses prior knowledge to augment the supervised experience; model, which uses prior knowledge to reduce the size of the hypothesis space; and algorithm, which uses prior knowledge to alter the search for the best hypothesis in the given hypothesis space.
  • OpenAlex ID:W2944378183
  • OpenAlex DOI:10.48550/arxiv.1904.05046
  • DOI:10.48550/arxiv.1904.05046
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/1904.05046
  • OpenAlex更新:2026-08-22
  • 待LLM分类:否
  • 成熟度:research
  • 场景:小样本学习、元学习
  • 标题中文:基于少量样本的泛化:小样本学习综述
  • TLDR中文:一篇全面综述,旨在深入理解 Few-shot Learning,并从三个维度对 FSL 方法进行分类:数据层面——利用先验知识扩充监督经验;模型层面——利用先验知识缩小假设空间规模;算法层面——利用先验知识改变在给定假设空间中对最优假设的搜索方式
  • 来源文件
  • [OpenAlex discover]
  • [S2 enrich]