Skip to content
master
Go to file
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 

README.md

Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation (DRCN)

This code is an implementation of the DRCN algorithm presented in [1].

[1] M. Ghifary, W. B. Kleijn, M. Zhang, D. Balduzzi, and W. Li. "Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation (DRCN)", European Conference on Computer Vision (ECCV), 2016

Contact:

Muhammad Ghifary (mghifary@gmail.com)

Requirements

  • Python 2.7
  • Tensorflow-1.0.1
  • Keras-2.0.0
  • numpy
  • h5py

Usage

To run the experiment with the (grayscaled) SVHN dataset as the source domain and the MNIST dataset as the target domain

python main_sm.py

The core algorithm is implemented in drcn.py. Data augmentation and denoising strategies are included as well.

Results

The source to target reconstruction below (SVHN as the source) indicates the successful training of DRCN.

python reconstruct_images.py

alt text

The classification accuracies of one DRCN run are plotted as follows -- the results may vary due to the randomness:

python plot_results.py

alt text

About

No description or website provided.

Topics

Resources

Releases

No releases published

Packages

No packages published

Languages

You can’t perform that action at this time.