論文筆記（三） 【Learning from Simulated and Unsupervised Images through Adversarial Training】
論文地址：論文 一、論文記錄 1.摘要 因爲隨着訓練技巧的提升，使用合成（產生）的圖片進行訓練，避免了人工註釋的麻煩。但是存在着一個問題，就是合成圖片與真實圖片的分佈存在着一定的差距。爲了解決這一問題，本文提出了Simulated + Unsupervised（仿真+無監督）learning的方法。具體來說是通過沒有標籤的真實圖片來提高仿真器生成圖片的真實性，同時還保持原有合成圖片的註釋信息
相關文章
- 1. 【paper 2】Learning from Simulated and Unsupervised Images through Adversarial Training
- 2. Learning from Simulated and Unsupervised Images through Adversarial Training：解析simGAN
- 3. 對抗學習之Learning from Simulated and Unsupervised Images through Adversarial Training
- 4. 論文筆記：Learning task-oriented grasping for tool manipulation from simulated self-supervision
- 5. 論文筆記：Learning Denoising from Single Noisy Images
- 6. CariGAN: Caricature Generation through Weakly Paired Adversarial Learning論文筆記
- 7. CVPR 2017【論文筆記】Unsupervised Learning of Depth and Ego-Motion from Video
- 8. 《Unsupervised Learning of Depth and Ego-Motion from Video》論文筆記
- 9. 【論文筆記】Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
- 10. [論文翻譯]Intramodality Domain Adaptation Using Self Ensembling and Adversarial Training
- 更多相關文章...
- • Docker images 命令 - Docker命令大全
- • ASP.NET Razor - 標記 - ASP.NET 教程
- • Tomcat學習筆記（史上最全tomcat學習筆記）
- • 三篇文章瞭解 TiDB 技術內幕 —— 說計算
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. 【paper 2】Learning from Simulated and Unsupervised Images through Adversarial Training
- 2. Learning from Simulated and Unsupervised Images through Adversarial Training：解析simGAN
- 3. 對抗學習之Learning from Simulated and Unsupervised Images through Adversarial Training
- 4. 論文筆記：Learning task-oriented grasping for tool manipulation from simulated self-supervision
- 5. 論文筆記：Learning Denoising from Single Noisy Images
- 6. CariGAN: Caricature Generation through Weakly Paired Adversarial Learning論文筆記
- 7. CVPR 2017【論文筆記】Unsupervised Learning of Depth and Ego-Motion from Video
- 8. 《Unsupervised Learning of Depth and Ego-Motion from Video》論文筆記
- 9. 【論文筆記】Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
- 10. [論文翻譯]Intramodality Domain Adaptation Using Self Ensembling and Adversarial Training