Re-weighted adversarial adaptation network for unsupervised domain adaptation
摘要主要强调以下几点： 1. 当domain discrepancy比较大的时候，文章中方法的性能比其余方法要好的多（实验部分的确如此） 2. re-weighted：在训练discriminator D的时候，每一个source sample并不是同等重要，weight取决于label 3. 在匹配source sample和target sample的特征分布的时候，用的是基于EM 距离的OT
相关文章
- 1. Domain Adaptation 与 Generative Adversarial Network
- 2. Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- 3. [cvpr2017]Deep Hashing Network for Unsupervised Domain Adaptation
- 4. Multi-Adversarial Domain Adaptation
- 5. Geodesic flow kernel for unsupervised domain adaptation
- 6. [cvpr2017]Unsupervised Pixel–Level Domain Adaptation with Generative Adversarial Networks
- 7. ADDA: Adversarial Discriminative Domain Adaptation
- 8. [cvpr2017]Adversarial Discriminative Domain Adaptation
- 9. Unsupervised Domain Adaptation by Backpropagation(2015)
- 10. 2019 AAAI Transferable Attention for Domain Adaptation
- 更多相关文章...
- • Swift for 循环 - Swift 教程
- • Scala for循环 - Scala教程
- • Flink 数据传输及反压详解
- • 算法总结-广度优先算法
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. Domain Adaptation 与 Generative Adversarial Network
- 2. Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- 3. [cvpr2017]Deep Hashing Network for Unsupervised Domain Adaptation
- 4. Multi-Adversarial Domain Adaptation
- 5. Geodesic flow kernel for unsupervised domain adaptation
- 6. [cvpr2017]Unsupervised Pixel–Level Domain Adaptation with Generative Adversarial Networks
- 7. ADDA: Adversarial Discriminative Domain Adaptation
- 8. [cvpr2017]Adversarial Discriminative Domain Adaptation
- 9. Unsupervised Domain Adaptation by Backpropagation(2015)
- 10. 2019 AAAI Transferable Attention for Domain Adaptation