Paper Reading: Adversarial PoseNet


Note: this post is only meant for personal digestion and interpretation. It is incomplete and may mislead readers.

Multi-Task Generative Network

Loss

Pose Discriminator

Confidence Discriminator

Training

Pose Discriminator

Confidence Discriminator

Final Objective Function

Note

Problems

  • Using of conditional GAN ( RMS threshold and distance threshold )
  • Result comparison: some compared to 2-stacked hourglass and some compared to four-stacked ( and using of word ‘2-stacked’ and ‘four-stacked’ )
  • Wrong description ( Ablation Study -> Multi-task )

Author: Texot
Reprint policy: All articles in this blog are used except for special statements CC BY 4.0 reprint polocy. If reproduced, please indicate source Texot !
 Previous
Paper Reading: Learning Feature Pyramids for Human Pose Estimation Paper Reading: Learning Feature Pyramids for Human Pose Estimation
Note: this post is only meant for personal digestion and interpretation. It is incomplete and may mislead readers. Int
2017-11-07
Next 
DIY微信iOS多开 DIY微信iOS多开
为了方便登录微信小号,打算自己动手做一个微信分身。过程和最主要的代码参考了FishChat及其作者的相关文章。以下内容主要为一些个人用途的记录。 Articles iOS逆向 给微信添加新功能 先看到这篇文章,屏蔽群消息等功能,并顺着文章找
2017-10-02
  TOC