ScholarGate
助手
Machine learningMachine learning

自监督迁移学习

自监督迁移学习结合了两种强大的范式：模型首先使用自监督的辅助任务从无标签数据中学习丰富的表征，然后这些学到的表征被迁移并在一项下游任务上进行微调，而该任务只有有限的有标签数据。这种方法是自然语言处理（NLP）中的BERT以及计算机视觉中的SimCLR和DINO等里程碑式系统的基础，极大地减少了许多领域对有标签数据的需求。

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.

自监督迁移学习
少样本学习度量学习自监督少样本学习自监督学习半监督学习迁移学习

来源

  1. Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 1597–1607. link ↗
  2. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT 2019, 4171–4186. Association for Computational Linguistics. DOI: 10.18653/v1/N19-1423 ↗

如何引用本页

ScholarGate. (2026, June 3). Self-supervised Pre-training for Transfer Learning. ScholarGate. https://scholargate.app/zh/machine-learning/self-supervised-transfer-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 — Self-supervised Transfer learning (Self-supervised Pre-training for Transfer Learning). 于 2026-06-15 检索自 https://scholargate.app/zh/machine-learning/self-supervised-transfer-learning · 数据集： https://doi.org/10.5281/zenodo.20539026