Skip to content
"Unified Deep Supervised Domain Adaptation and Generalization" (ICCV 2017)
Branch: master
Clone or download
Latest commit 440ac9c Aug 16, 2017
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
row_data main Aug 15, 2017
Initialization.py main Aug 15, 2017
README.md main Aug 15, 2017
main.py
row_data.7z.001 main Aug 15, 2017
row_data.7z.002 main Aug 15, 2017
row_data.7z.003 main Aug 15, 2017
row_data.7z.004 main Aug 15, 2017
row_data.7z.005
row_data.7z.006 main Aug 15, 2017

README.md

CCSA: "Unified Deep Supervised Domain Adaptation and Generalization" (ICCV 2017)

Requiremenrts

keras and numpy

Introduction

This repository provides the implementation of the paper "Unified Deep Supervised Domain Adaptation and Generalization" published in ICCV 2017. It also contains the training/testing splits of two cross domain adaptation task (MNIST->USPS and USPS->MNIST).

We are interested in the supervised domain adaptation when very few labeled target samples are available in training (from 1 to 7).

Experimental setting involves randomly selecting 2000 images from MNIST and 1800 images from USPS. Here, we randomly selected n labeled samples per class from target domain data and used them in training. We evaluated our approach for n ranging from 1 to 7 and repeated each experiment 10 times. Therefore, we provided data we used to generate the results. Data files are located in the 'row_data' subdirectory.

"We encourage researchers to use this data for comparison."

Implementation

To reproduce the results of the paper you just need to run main.py. There are three main parameters:

  1. sample_per_class = 1 or 2 or ... or 7 (sample_per_class specifies the number of labeled target data per class.)

  2. repetition = 0 or 2 or ... or 9. (We repeat the experiments 10 times and report the average accuracies.)

  3. domain_adaptation_task = 'MNIST_to_USPS' or 'USPS_to_MNIST'

There are some other hyperparameters that you may change for the new dataset.

Citation

@InProceedings{motiian2017CCSA, Title = {Unified Deep Supervised Domain Adaptation and Generalization},

Author = {Motiian, Saeid and Piccirilli, Marco and Adjeroh, Donald A. and Doretto, Gianfranco},

Booktitle = {IEEE International Conference on Computer Vision (ICCV)},

Year = {2017}}

For more information:

http://vision.csee.wvu.edu/~motiian/Details/CCSA.html

You can’t perform that action at this time.