A PyTorch implementation for paper Unsupervised Domain Adaptation by Backpropagation
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
wogong 793969a3ca using random seed. 5 years ago
core remove legacy code. 5 years ago
datasets using random seed. 5 years ago
experiments update SYNSIGNS-GTSRB source only expe result, finally succeed. 5 years ago
models update SYNSIGNS-GTSRB source only expe result, finally succeed. 5 years ago
utils update SYNSIGNS-GTSRB source only expe result, finally succeed. 5 years ago
.gitignore add jupyter notebook. 5 years ago
LICENSE Initial commit 7 years ago
README.md update readme 5 years ago
dann.ipynb add jupyter notebook. 5 years ago
requirements.txt add requirements 5 years ago

README.md

PyTorch-DANN

A PyTorch implementation for paper Unsupervised Domain Adaptation by Backpropagation

InProceedings (icml2015-ganin15)
Ganin, Y. & Lempitsky, V.
Unsupervised Domain Adaptation by Backpropagation
Proceedings of the 32nd International Conference on Machine Learning, 2015

Environment

  • Python 3.6
  • PyTorch 1.0

Note

  • MNISTmodel()
    • basically the same network structure as proposed in the paper, expect for adding dropout layer in feature extractor
    • large gap exsits between with and w/o dropout layer
    • better result than paper
  • SVHNmodel()
    • network structure proposed in the paper may be wrong for both 32x32 and 28x28 inputs
    • change last conv layer's filter to 4x4, get similar(actually higher) result
  • GTSRBmodel()
  • AlexModel
    • not successful, mainly due to the pretrained model difference

Result

MNIST-MNISTM SVHN-MNIST Amazon-Webcam SYNDIGITS-SVHN SYNSIGNS-GTSRB
Source Only 0.5225 0.5490 0.6420 0. 0.
DANN(paper) 0.7666 0.7385 0.7300 0.9109 0.7900
This Repo Source Only - - - 0. 0.7650
This Repo 0.8400 0.7339 0.6528 0.8200 0.6200

Credit