Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation

Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi, Wen Li

ECCV 2016 pp. 597-613

doi:10.1007/978-3-319-46493-0_36 /eccv/2016/ghifary2016eccv-deep/

Abstract

In this paper, we propose a novel unsupervised domain adaptation algorithm based on deep learning for visual object recognition. Specifically, we design a new model called Deep Reconstruction-Classification Network (DRCN), which jointly learns a shared encoding representation for two tasks: (i) supervised classification of labeled source data, and (ii) unsupervised reconstruction of unlabeled target data. In this way, the learnt representation not only preserves discriminability, but also encodes useful information from the target domain. Our new DRCN model can be optimized by using backpropagation similarly as the standard neural networks.

PDF ECCV Semantic Scholar

Cite

Text

Ghifary et al. "Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46493-0_36

Markdown

[Ghifary et al. "Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/ghifary2016eccv-deep/) doi:10.1007/978-3-319-46493-0_36

BibTeX

@inproceedings{ghifary2016eccv-deep,
  title     = {{Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation}},
  author    = {Ghifary, Muhammad and Kleijn, W. Bastiaan and Zhang, Mengjie and Balduzzi, David and Li, Wen},
  booktitle = {European Conference on Computer Vision},
  year      = {2016},
  pages     = {597-613},
  doi       = {10.1007/978-3-319-46493-0_36},
  url       = {https://mlanthology.org/eccv/2016/ghifary2016eccv-deep/}
}