《Domain Agnostic Learning with Disentangled Representations》代码

《Domain Agnostic Learning with Disentangled Representations》代码_第1张图片

文章目录

  • `class_loss` 分类交叉熵损失_论文公式(2)
  • `ring_loss` Ring-style Normalization_论文公式(8)
  • `mutual_information`_论文公式(5/6/7)
  • `confusion_loss` L e n t L_{ent} Lent_论文公式(3)
  • `alignment_loss`
  • `Reconstruction`重构损失_论文公式(1)
  • 与论文对比

class_loss 分类交叉熵损失_论文公式(2)

《Domain Agnostic Learning with Disentangled Representations》代码_第2张图片

ring_loss Ring-style Normalization_论文公式(8)

《Domain Agnostic Learning with Disentangled Representations》代码_第3张图片

mutual_information_论文公式(5/6/7)

《Domain Agnostic Learning with Disentangled Representations》代码_第4张图片

confusion_loss L e n t L_{ent} Lent_论文公式(3)

《Domain Agnostic Learning with Disentangled Representations》代码_第5张图片

alignment_loss

《Domain Agnostic Learning with Disentangled Representations》代码_第6张图片
FD就是论文中的DI

Specifically, we leverage a domain identifier D I DI DI, which takes the disentangled feature ( f d i f_{di} fdi or f d s f_{ds} fds ) as input and outputs the domain label l f l_f lf(source or target).

Reconstruction重构损失_论文公式(1)

《Domain Agnostic Learning with Disentangled Representations》代码_第7张图片

与论文对比

论文
《Domain Agnostic Learning with Disentangled Representations》代码_第8张图片

代码流程
《Domain Agnostic Learning with Disentangled Representations》代码_第9张图片

你可能感兴趣的:(Python,#,代码,#,论文,python)