論文翻譯:Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
摘要 監督學習的成功依賴於假設訓練和測試數據來自相同的潛在分佈，這在實踐中往往是無效的，因爲潛在的分佈轉移。鑑於此，現有的非監督域自適應方法大多集中於實現域不變表示和小源域誤差。然而，最近的研究表明，這並不足以保證在目標域上有良好的泛化，事實上，在標籤分佈位移下是有害的。此外，在許多實際應用中，從目標領域獲取少量標記數據並使用它們來促進源數據的模型訓練往往是可行的。受上述觀察的啓發，本文第一次提出
相關文章
- 1. 【論文翻譯】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. [論文翻譯]Intramodality Domain Adaptation Using Self Ensembling and Adversarial Training
- 5. Deep Learning, NLP, and Representations翻譯學習
- 6. 《Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks》 論文翻譯筆記
- 7. [cvpr2017]Joint Geometrical and Statistical Alignment for Visual Domain Adaptation
- 8. [MICCAI2019]Unsupervised Domain Adaptation via Disentangled Representations
- 9. 論文筆記：Domain Adaptation for Image Dehazing
- 10. 【論文翻譯】Deep Residual Learning for Image Recognition
- 更多相關文章...
- • Eclipse 編譯項目 - Eclipse 教程
- • Swift for 循環 - Swift 教程
- • RxJava操作符（七）Conditional and Boolean
- • Scala 中文亂碼解決
相關標籤/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。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. 【論文翻譯】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. [論文翻譯]Intramodality Domain Adaptation Using Self Ensembling and Adversarial Training
- 5. Deep Learning, NLP, and Representations翻譯學習
- 6. 《Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks》 論文翻譯筆記
- 7. [cvpr2017]Joint Geometrical and Statistical Alignment for Visual Domain Adaptation
- 8. [MICCAI2019]Unsupervised Domain Adaptation via Disentangled Representations
- 9. 論文筆記：Domain Adaptation for Image Dehazing
- 10. 【論文翻譯】Deep Residual Learning for Image Recognition