对比学习（联邦相关）--持续更新

MrPleom

已于 2023-03-31 18:18:28 修改

阅读量375

点赞数

文章标签：机器学习

于 2023-03-27 19:30:44 首次发布

本文链接：https://blog.csdn.net/weixin_43773486/article/details/129801203

版权

文章探讨了对比学习在视觉特征表示中的应用，特别是无监督和自我监督的方法，如MoCo和CMC。同时，提到了联邦学习在保护数据隐私方面的贡献，如FederatedUnsupervisedRepresentationLearning，强调了这些技术在不依赖大量标注数据的情况下提升模型性能的能力。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

对比学习方法——来自联邦对比学习

自监督学习

Jing L, Tian Y. Self-supervised visual feature learning with deep neural networks: A survey[J]. IEEE transactions on pattern analysis and machine intelligence, 2020, 43(11): 4037-4058.（谷歌引用1202）
Grill J B, Strub F, Altché F, et al. Bootstrap your own latent-a new approach to self-supervised learning[J]. Advances in neural information processing systems, 2020, 33: 21271-21284.（谷歌引用3603）
以下四篇文章在视觉表征方面取得了先进的成果
Chen T, Kornblith S, Norouzi M, et al. A simple framework for contrastive learning of visual representations[C]//International conference on machine learning. PMLR, 2020: 1597-1607.（谷歌引用9056）
Chen T, Kornblith S, Swersky K, et al. Big self-supervised models are strong semi-supervised learners[J]. Advances in neural information processing systems, 2020, 33: 22243-22255.（谷歌引用1399）
He K, Fan H, Wu Y, et al. Momentum contrast for unsupervised visual representation learning[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 9729-9738.（谷歌引用6463）
Misra I, Maaten L. Self-supervised learning of pretext-invariant representations[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 6707-6717.（谷歌引用1040）
Chen T, Kornblith S, Norouzi M, et al. A simple framework for contrastive learning of visual representations[C]//International conference on machine learning. PMLR, 2020: 1597-1607.典型的对比学习框架（谷歌引用量9056）
Sohn K. Improved deep metric learning with multi-class n-pair loss objective[J]. Advances in neural information processing systems, 2016, 29.对比损失定义（谷歌引用1628）
Oord A, Li Y, Vinyals O. Representation learning with contrastive predictive coding[J]. arXiv preprint arXiv:1807.03748, 2018.对比学习框架CPC（谷歌引用量4651）
Tian Y, Krishnan D, Isola P. Contrastive multiview coding[C]//Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XI 16. Springer International Publishing, 2020: 776-794.对比学习框架CMC（谷歌引用量1613）
He K, Fan H, Wu Y, et al. Momentum contrast for unsupervised visual representation learning[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 9729-9738.对比学习框架MoCo（谷歌引用量6463）
Zhang F, Kuang K, You Z, et al. Federated unsupervised representation learning[J]. arXiv preprint arXiv:2010.08982, 2020.联邦无监督对比学习（谷歌引用量59）
Chen T, Kornblith S, Norouzi M, et al. A simple framework for contrastive learning of visual representations[C]//International conference on machine learning. PMLR, 2020: 1597-1607. 对比学习框架（谷歌引用量9151）