learning
/
DeepLearning-500-questions
mirror of https://github.com/scutan90/DeepLearning-500-questions.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add 2019CVPR Paper and examples for GAN 

Add 2019CVPR Paper and examples for GAN
This commit is contained in:
Zhedong Zheng 2019-07-11 23:37:13 +10:00 committed by GitHub
parent a04c65c016
commit 4658f1f51c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ch07_生成对抗网络(GAN)/ch7.md
View File

@ -455,6 +455,9 @@ cycleGAN模型较好的解决了无监督图像转换问题，可是这种单一
![cycleGAN数据增广](./img/ch7/cycleGAN数据增广.png) ![cycleGAN数据增广](./img/ch7/cycleGAN数据增广.png)
​ 对于每一对摄像头都训练一个cycleGAN，这样就可以实现将一个摄像头下的数据转换成另一个摄像头下的数据，但是内容（人物）保持不变。 ​ 对于每一对摄像头都训练一个cycleGAN，这样就可以实现将一个摄像头下的数据转换成另一个摄像头下的数据，但是内容（人物）保持不变。
在CVPR19中，[9]进一步提升了图像的生成质量，进行了“淘宝换衣”式的高质量图像生成（如下图），提供了更高质量的行人训练数据。
![DG-Net数据增广](https://github.com/NVlabs/DG-Net/raw/master/NxN.jpg)
### 7.5.2 图像超分辨与图像补全 ### 7.5.2 图像超分辨与图像补全
@ -482,5 +485,7 @@ cycleGAN模型较好的解决了无监督图像转换问题，可是这种单一
[8] Donahue C , Li B , Prabhavalkar R . Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition[J]. 2017. [8] Donahue C , Li B , Prabhavalkar R . Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition[J]. 2017.
[9] Zheng, Z., Yang, X., Yu, Z., Zheng, L., Yang, Y., & Kautz, J. Joint discriminative and generative learning for person re-identification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[C]. 2019.