Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
目錄 摘要 1、簡介 2、相關工作 2.1、語義分割的域適配 2.2、風格遷移 2.3、紋理和形狀 3、方法 3.1、程式化的GTA5和SYNTHIA 3.2、階段1 3.3、階段2 3.4、訓練目標函數 4、實驗 5、討論 5.1、和基於CycleGAN的方法的比較 5.2、消融研究 5.3、魯棒性測試 5.4、定性測試
相關文章
- 1. Bidirectional Learning for Domain Adaptation of Semantic Segmentation詳讀
- 2. Fully Convolutional Adaptation Networks for Semantic Segmentation
- 3. Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation
- 4. [cvpr2017]Learning an Invariant Hilbert Space for Domain Adaptation
- 5. Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
- 6. 論文閱讀 | A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes
- 7. 極簡筆記 Fully Convolutional Adaptation Networks for Semantic Segmentation
- 8. 論文翻譯:Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
- 9. Review of Semantic Segmentation with Deep Learning
- 10. Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- 更多相關文章...
- • Scala for循環 - Scala教程
- • Swift for 循環 - Swift 教程
- • Composer 安裝與使用
- • Java Agent入門實戰（三）-JVM Attach原理與使用
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. Bidirectional Learning for Domain Adaptation of Semantic Segmentation詳讀
- 2. Fully Convolutional Adaptation Networks for Semantic Segmentation
- 3. Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation
- 4. [cvpr2017]Learning an Invariant Hilbert Space for Domain Adaptation
- 5. Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
- 6. 論文閱讀 | A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes
- 7. 極簡筆記 Fully Convolutional Adaptation Networks for Semantic Segmentation
- 8. 論文翻譯:Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
- 9. Review of Semantic Segmentation with Deep Learning
- 10. Maximum Classifier Discrepancy for Unsupervised Domain Adaptation