论文翻译:Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
摘要 监督学习的成功依赖于假设训练和测试数据来自相同的潜在分布，这在实践中往往是无效的，因为潜在的分布转移。鉴于此，现有的非监督域自适应方法大多集中于实现域不变表示和小源域误差。然而，最近的研究表明，这并不足以保证在目标域上有良好的泛化，事实上，在标签分布位移下是有害的。此外，在许多实际应用中，从目标领域获取少量标记数据并使用它们来促进源数据的模型训练往往是可行的。受上述观察的启发，本文第一次提出
相关文章
- 1. 【论文翻译】Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing
- 2. [cvpr2017]Learning an Invariant Hilbert Space for Domain Adaptation
- 3. Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
- 4. [论文翻译]Intramodality Domain Adaptation Using Self Ensembling and Adversarial Training
- 5. Deep Learning, NLP, and Representations翻译学习
- 6. 《Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks》 论文翻译笔记
- 7. [cvpr2017]Joint Geometrical and Statistical Alignment for Visual Domain Adaptation
- 8. [MICCAI2019]Unsupervised Domain Adaptation via Disentangled Representations
- 9. 论文笔记：Domain Adaptation for Image Dehazing
- 10. 【论文翻译】Deep Residual Learning for Image Recognition
- 更多相关文章...
- • Eclipse 编译项目 - Eclipse 教程
- • Swift for 循环 - Swift 教程
- • RxJava操作符（七）Conditional and Boolean
- • Scala 中文乱码解决
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. 【论文翻译】Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing
- 2. [cvpr2017]Learning an Invariant Hilbert Space for Domain Adaptation
- 3. Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
- 4. [论文翻译]Intramodality Domain Adaptation Using Self Ensembling and Adversarial Training
- 5. Deep Learning, NLP, and Representations翻译学习
- 6. 《Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks》 论文翻译笔记
- 7. [cvpr2017]Joint Geometrical and Statistical Alignment for Visual Domain Adaptation
- 8. [MICCAI2019]Unsupervised Domain Adaptation via Disentangled Representations
- 9. 论文笔记：Domain Adaptation for Image Dehazing
- 10. 【论文翻译】Deep Residual Learning for Image Recognition