Show, Attend and Translate: Unsupervised Image Translation with Self-Regularization and Attention 解读
本文提出了一种结合Attention机制和self-Regularization的无监督图像域转换模型。 问题 为了解决两个域间的图像转换问题，需要学习从一个域到另一个域的映射，将X域中的图像转换到Y域。 本文的目的是使生成的图像看起来和源图像(X域)是相似的，同时具备Y域图像的特征。 如上图所示，图像从Horse域转换到了Zebra域，但是背景部分并没有变化。 方法 由于现在的图像转换方法经常会
相关文章
- 1. 《Show, Attend and Tell: Neural Image Caption Generation with Visual Attention》阅读笔记
- 2. Unsupervised Attention-guided Image-to-Image Translation 解读
- 3. [Paper Reading] Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- 4. [Image Caption系列(1)] Show attend and tell论文解读
- 5. image caption解读系列（二）：《Show, Attend and Tell_Neural Image Caption》
- 6. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention论文阅读笔记
- 7. attention(show, attention and tell: neural image caption generation with visual attention)
- 8. 零基础学nlp【5】 hard attention 和 soft attention（Show, attend and tell: Neural image caption generation ）
- 9. attention model--Neural machine translation by jointly learning to align and translate论文解读
- 10. Translation with a Sequence to Sequence Network and Attention
- 更多相关文章...
- • XSL-FO table-and-caption 对象 - XSL-FO 教程
- • W3C RDF and OWL 活动 - W3C 教程
- • RxJava操作符（七）Conditional and Boolean
- • JDK13 GA发布：5大特性解读
相关标签/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。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 《Show, Attend and Tell: Neural Image Caption Generation with Visual Attention》阅读笔记
- 2. Unsupervised Attention-guided Image-to-Image Translation 解读
- 3. [Paper Reading] Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- 4. [Image Caption系列(1)] Show attend and tell论文解读
- 5. image caption解读系列（二）：《Show, Attend and Tell_Neural Image Caption》
- 6. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention论文阅读笔记
- 7. attention(show, attention and tell: neural image caption generation with visual attention)
- 8. 零基础学nlp【5】 hard attention 和 soft attention（Show, attend and tell: Neural image caption generation ）
- 9. attention model--Neural machine translation by jointly learning to align and translate论文解读
- 10. Translation with a Sequence to Sequence Network and Attention