ScholarGate
助手
Machine learningDeep learning / NLP / CV

自监督生成对抗网络

自监督生成对抗网络（Self-supervised GAN）在标准生成对抗网络（GAN）的基础上增加了一个或多个自监督辅助任务，例如预测图像旋转角度或图像块位置，这些任务可以稳定对抗训练，并生成一个能够从无标签数据中学习丰富、可迁移表示的判别器，而无需人工标注。

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.

自监督生成对抗网络
生成对抗网络自监督卷积神经网络自监督变分自编码器Semi-supervised GANVision Transformer

来源

  1. Chen, T., Zhai, X., Ritter, M., Lucic, M., & Houlsby, N. (2019). Self-Supervised GANs via Auxiliary Rotation Loss. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12154–12163. link ↗
  2. Liu, X., Zhang, F., Hou, Z., Mian, L., Wang, Z., Zhang, J., & Tang, J. (2021). Self-supervised learning: Generative or contrastive. IEEE Transactions on Knowledge and Data Engineering, 35(1), 857–876. DOI: 10.1109/TKDE.2021.3090866 ↗

如何引用本页

ScholarGate. (2026, June 3). Self-supervised Generative Adversarial Network. ScholarGate. https://scholargate.app/zh/deep-learning/self-supervised-gan

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 →

被引用于

Semi-supervised GAN

发现本页有问题？报告或提出修改建议 →

ScholarGate — Self-supervised GAN (Self-supervised Generative Adversarial Network). 于 2026-06-15 检索自 https://scholargate.app/zh/deep-learning/self-supervised-gan · 数据集： https://doi.org/10.5281/zenodo.20539026