-
Notifications
You must be signed in to change notification settings - Fork 16
A simple implementation of domain adversarial training with GAN loss in Keras
License
ssamot/DANN-keras
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
A keras implementation of a custom version of adversarial domain adaptation Some code is borrowed from this repo [https://github.com/pumpikano/tf-dann/blob/master/Blobs-DANN.ipynb] The method implemented combines these three papers: Ganin, Yaroslav, and Victor Lempitsky. "Unsupervised Domain Adaptation by Backpropagation." International Conference on Machine Learning. 2015.(http://sites.skoltech.ru/compvision/projects/grl/files/paper.pdf) [Tzeng, Eric, et al. "Adversarial discriminative domain adaptation." Computer Vision and Pattern Recognition (CVPR). Vol. 1. No. 2. 2017.](http://openaccess.thecvf.com/content_cvpr_2017/papers/Tzeng_Adversarial_Discriminative_Domain_CVPR_2017_paper.pdf) [Li, Yanghao, et al. "Revisiting batch normalization for practical domain adaptation." arXiv preprint arXiv:1603.04779 (2016).](https://arxiv.org/abs/1603.04779)
About
A simple implementation of domain adversarial training with GAN loss in Keras
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published