Transferrable Prototypical Networks for Unsupervised Domain Adaptation读书笔记
这篇文章是cvpr2019的一篇域适应的文章，我觉得很不错，和大家一起分享一下 在这篇文章里，通过对每个类到原型的距离的重新映射，学习一个嵌入空间并执行分类。具体地说，提出了可转移的原型网络(TPN)来进行自适应，使源域和目标域的每个类的原型在嵌入空间上都很接近，并且原型在源和目标数据上分别预测的分数分布也很简单。从技术上讲，TPN最初将每个目标示例与源域中最近的原型匹配，并将这个原型作为示例的“
相关文章
- 1. CVPR2019 Transferrable Prototypical Networks for Unsupervised Domain Adaptation
- 2. Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- 3. Geodesic flow kernel for unsupervised domain adaptation
- 4. Re-weighted adversarial adaptation network for unsupervised domain adaptation
- 5. [论文阅读笔记@2019.6] Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- 6. Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling读书笔记
- 7. [cvpr2017]Unsupervised Pixel–Level Domain Adaptation with Generative Adversarial Networks
- 8. Unsupervised Domain Adaptation with Residual Transfer Networks（2017）
- 9. Unsupervised domain adaptation with residual transfer networks(NIPS 2016)
- 10. Transferable Attention for Domain Adaptation阅读笔记
- 更多相关文章...
- • Eclipse 添加书签 - Eclipse 教程
- • ASP.NET Razor - 标记 - ASP.NET 教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • JDK13 GA发布：5大特性解读
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. CVPR2019 Transferrable Prototypical Networks for Unsupervised Domain Adaptation
- 2. Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- 3. Geodesic flow kernel for unsupervised domain adaptation
- 4. Re-weighted adversarial adaptation network for unsupervised domain adaptation
- 5. [论文阅读笔记@2019.6] Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- 6. Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling读书笔记
- 7. [cvpr2017]Unsupervised Pixel–Level Domain Adaptation with Generative Adversarial Networks
- 8. Unsupervised Domain Adaptation with Residual Transfer Networks（2017）
- 9. Unsupervised domain adaptation with residual transfer networks(NIPS 2016)
- 10. Transferable Attention for Domain Adaptation阅读笔记