Domain Adaptive Classification
Abstract
We propose an unsupervised domain adaptation method that exploits intrinsic compact structures of categories across different domains using binary attributes. Our method directly optimizes for classification in the target domain. The key insight is finding attributes that are discriminative across categories and predictable across domains. We achieve a performance that significantly exceeds the state-of-the-art results on standard benchmarks. In fact, in many cases, our method reaches the same-domain performance, the upper bound, in unsupervised domain adaptation scenarios.
Cite
Text
Mirrashed and Rastegari. "Domain Adaptive Classification." International Conference on Computer Vision, 2013. doi:10.1109/ICCV.2013.324Markdown
[Mirrashed and Rastegari. "Domain Adaptive Classification." International Conference on Computer Vision, 2013.](https://mlanthology.org/iccv/2013/mirrashed2013iccv-domain/) doi:10.1109/ICCV.2013.324BibTeX
@inproceedings{mirrashed2013iccv-domain,
title = {{Domain Adaptive Classification}},
author = {Mirrashed, Fatemeh and Rastegari, Mohammad},
booktitle = {International Conference on Computer Vision},
year = {2013},
doi = {10.1109/ICCV.2013.324},
url = {https://mlanthology.org/iccv/2013/mirrashed2013iccv-domain/}
}