A DIRT-T APPROACH TO UNSUPERVISED DOMAIN ADAPTATION
這篇是一篇領域自適應（domain adaption，遷移學習的一種）方面的文章，因爲我本身的研究方向不是這個，只是老師推薦看的所以我就隨便做點筆記，就當做整理一下自己的思路吧。說實話，這裏肯定有很多專業術語上面的問題或者其他方面的問題，麻煩大家多多包涵啦。 基本問題和動機： 領域自適應（Domain adaptation）是指利用源域（source domain）中的標記數據來學習一個可以應用於
相關文章
- 1. Domain Adaptation for Object Recognition: An Unsupervised Approach
- 2. Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-ID
- 3. Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-id
- 4. Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- 5. Geodesic flow kernel for unsupervised domain adaptation
- 6. 論文閱讀 | A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes
- 7. Re-weighted adversarial adaptation network for unsupervised domain adaptation
- 8. [MICCAI2019]Unsupervised Domain Adaptation via Disentangled Representations
- 9. Unsupervised Domain Adaptation by Backpropagation(2015)
- 10. [cvpr2017]Unsupervised Pixel–Level Domain Adaptation with Generative Adversarial Networks
- 更多相關文章...
- • ASP ServerVariables 集合 - ASP 教程
- • PHP setcookie() 函數 - PHP參考手冊
- • 委託模式
- • Kotlin學習（二）基本類型
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. Domain Adaptation for Object Recognition: An Unsupervised Approach
- 2. Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-ID
- 3. Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-id
- 4. Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- 5. Geodesic flow kernel for unsupervised domain adaptation
- 6. 論文閱讀 | A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes
- 7. Re-weighted adversarial adaptation network for unsupervised domain adaptation
- 8. [MICCAI2019]Unsupervised Domain Adaptation via Disentangled Representations
- 9. Unsupervised Domain Adaptation by Backpropagation(2015)
- 10. [cvpr2017]Unsupervised Pixel–Level Domain Adaptation with Generative Adversarial Networks