Machine learningDeep learning / NLP / CV
基于卷积神经网络的迁移学习
基于卷积神经网络（CNN）的迁移学习，是指重用一个已在大规模数据集（通常是ImageNet）上训练好的CNN，并将其学到的特征检测器调整到新的、通常较小的目标数据集上。这使得研究人员无需从头开始训练CNN所需的巨大计算和数据资源，即可获得强大的图像识别性能。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
+4 more
来源
- Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI: 10.1109/TKDE.2009.191 ↗
- Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems (NeurIPS), 27, 3320–3328. link ↗
如何引用本页
ScholarGate. (2026, June 3). Transfer Learning with Convolutional Neural Network (Feature Extraction and Fine-Tuning). ScholarGate. https://scholargate.app/zh/deep-learning/transfer-learning-with-convolutional-neural-network
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 →