Learning to discover cross-domain relations with gan
Abstract 人類可以在無監督的情況下輕易地發現兩個東西之間的聯繫(或者說相同點), 而想讓機器學習的話需要人類給他們配對作爲ground truth然後再進行訓練. 爲了避免這種配對的麻煩, 提出了DiscoGAN Introduction 這篇文章把」尋找兩種圖片的關係」變成了」用一種風格的圖片生成另一種風格」(利用GAN),這是本文解決」尋找relation」的思路所在. 不需要人工配對
相關文章
- 1. [Deep-Learning-with-Python]GAN圖片生成
- 2. Paper：Sequence to Sequence Learning with Neural Networks
- 3. 論文筆記5：Integrating Probabilistic Extraction Models and Data Mining to Discover Relations and Patterns
- 4. An Introduction to Machine Learning with Python
- 5. Sutskever2014_Sequence to Sequence Learning with Neural Networks
- 6. [GAN-1] Learning Note
- 7. TuiGAN: Learning Versatile Image-to-ImageTranslation with Two Unpaired Images
- 8. GAN 論文大彙總
- 9. AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks
- 10. embedding entities and relations for learning and inference knowledge base
- 更多相關文章...
- • XSLT
- • XQuery 選擇 和 過濾 - XQuery 教程
- • 爲了進字節跳動，我精選了29道Java經典算法題，帶詳細講解
- • 算法總結-股票買賣
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. [Deep-Learning-with-Python]GAN圖片生成
- 2. Paper：Sequence to Sequence Learning with Neural Networks
- 3. 論文筆記5：Integrating Probabilistic Extraction Models and Data Mining to Discover Relations and Patterns
- 4. An Introduction to Machine Learning with Python
- 5. Sutskever2014_Sequence to Sequence Learning with Neural Networks
- 6. [GAN-1] Learning Note
- 7. TuiGAN: Learning Versatile Image-to-ImageTranslation with Two Unpaired Images
- 8. GAN 論文大彙總
- 9. AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks
- 10. embedding entities and relations for learning and inference knowledge base