翻译“Learning Transferable Features with Deep Adaptation Networks”
利用深度适应网络学习可迁移特征 摘 要：最近的研究表明深度神经网络可以学习可迁移特征，这些特征用于域适应时在新的任务上表现出很好的泛化能力。然而由于深度特征随着网络层数的增加由一般到特殊转变，特征的可迁移能力在网络高层急剧下降，极大地增加了域之间的差异性。因此减少不同数据集间的偏差，同时增加任务特征层的可迁移能力是非常重要的。在本文中，我们提出了一个新的深度适应网络（DAN)架构，把深度卷积神经
相关文章
- 1. Learning Transferable Features with Deep Adaptation Networks
- 2. 对于DAN方法的解读-Learning Transferable Features with Deep Adaptation Networks
- 3. How transferable are features in deep nerual networks? 【paper review】
- 4. [翻译]Learning Multiple Tasks with Deep Relationship Networks
- 5. How transferable are features in deep neural networks?
- 6. 《Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks》 论文翻译笔记
- 7. A Survey on Deep Transfer Learning 2018 翻译
- 8. [翻译]Learning Deep Features for Discriminative Localization
- 9. ImageNet Classification with Deep Convolutional Neural Networks （AlexNet）翻译
- 10. [翻译]FlowNet: Learning Optical Flow with Convolutional Networks
- 更多相关文章...
- • Eclipse 编译项目 - Eclipse 教程
- • Kotlin 使用命令行编译 - Kotlin 教程
- • Java Agent入门实战（一）-Instrumentation介绍与使用
- • Java Agent入门实战（三）-JVM Attach原理与使用
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. Learning Transferable Features with Deep Adaptation Networks
- 2. 对于DAN方法的解读-Learning Transferable Features with Deep Adaptation Networks
- 3. How transferable are features in deep nerual networks? 【paper review】
- 4. [翻译]Learning Multiple Tasks with Deep Relationship Networks
- 5. How transferable are features in deep neural networks?
- 6. 《Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks》 论文翻译笔记
- 7. A Survey on Deep Transfer Learning 2018 翻译
- 8. [翻译]Learning Deep Features for Discriminative Localization
- 9. ImageNet Classification with Deep Convolutional Neural Networks （AlexNet）翻译
- 10. [翻译]FlowNet: Learning Optical Flow with Convolutional Networks