ScholarGate
助手
Machine learningMachine learning

正则化少样本学习

正则化少样本学习通过显式的正则化机制（如权重衰减、Dropout、数据增强、标签平滑或流形约束）来增强标准的少样本学习流程，以减少对定义每个回合（episode）的微小支持集（support set）的过拟合。当每类只有一到三十个标记样本可用时，这能产生更具泛化能力的模型。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

登录

Method map

The neighbourhood of related methods — select a node to explore.

正则化少样本学习
少样本学习正则化迁移学习自监督学习半监督少样本学习迁移学习

来源

  1. Chen, W., Liu, Y., Kira, Z., Wang, Y. F., & Huang, J. (2019). A Closer Look at Few-Shot Classification. International Conference on Learning Representations (ICLR). link ↗
  2. Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J. B., & Isola, P. (2020). Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? European Conference on Computer Vision (ECCV). link ↗

如何引用本页

ScholarGate. (2026, June 3). Regularized Few-Shot Learning (Regularization-Enhanced Meta-Learning). ScholarGate. https://scholargate.app/zh/machine-learning/regularized-few-shot-learning

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side →

发现本页有问题？报告或提出修改建议 →

ScholarGate — Regularized Few-Shot Learning (Regularized Few-Shot Learning (Regularization-Enhanced Meta-Learning)). 于 2026-06-15 检索自 https://scholargate.app/zh/machine-learning/regularized-few-shot-learning · 数据集： https://doi.org/10.5281/zenodo.20539026