Skip to content
Branch: master
Find file History
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
..
Failed to load latest commit information.
MRAN.py add: MRAN code Sep 2, 2019
README.md add: MRAN code Sep 2, 2019
ResNet.py add: MRAN code Sep 2, 2019
data_loader.py
mmd.py add: MRAN code Sep 2, 2019

README.md

MRAN

A PyTorch implementation of 'Multi-representationadaptationnetworkforcross-domainimage classification'. The contributions of this paper are summarized as follows.

  • We are the first to learn multiple different domain-invariant representations by Inception Adaptation Module (IAM) for cross-domain image classification.
  • A novel Multi-Representation Adaptation Network (MRAN) is proposed to align distributions of multiple different representations which might contain more information about the images.

Requirement

  • python 3
  • pytorch 0.3.1
  • torchvision 0.2.0

Usage

  1. You can download Office31 dataset here. And then unrar dataset in ./dataset/.
  2. You can change the source_name and target_name in MRAN.py to set different transfer tasks.
  3. Run python MRAN.py.

Results on Office31

Method A - W D - W W - D A - D D - A W - A Average
MRAN 91.4±0.1 96.9±0.3 99.8±0.2 86.4±0.6 68.3±0.5 70.9±0.6 85.6

Reference

Zhu Y, Zhuang F, Wang J, et al. Multi-representation adaptation network for cross-domain image classification[J]. Neural Networks, 2019.

Contact

If you have a problem with the code, please contact zhuyongchun18s@ict.ac.cn.

You can’t perform that action at this time.