search

easezyc / deep-transfer-learning

A collection of implementations of deep domain adaptation algorithms
MIT License
889 stars 205 forks source link

Question about RevGrad #7

Closed anonymous1computervision closed 5 years ago

anonymous1computervision commented 5 years ago

In RevGrad, u used confusion_loss. My question why u used this loss as u already used critic loss (domain loss) and classification loss. Can u please explain a little bit on this?

easezyc commented 5 years ago

You could refer to "Simultaneous Deep Transfer Across Domains and Tasks".