Learning cross-domain semantic-visual relationships for transductive zero-shot learning

Fengmao Lv, Jianyang Zhang, Guowu Yang, Lei Feng, Yufeng Yu, Lixin Duan

Abstract

Highlights•We propose to address ZSL as a standard domain adaptation task.•A novel domain-specific batch normalization component is proposed to align domain gaps in semantic-visual fusions.•Extensive experiments show the effectiveness and robustness of our approach.
BibTeX
@article{lv2023learning,
  author = {Fengmao Lv and Jianyang Zhang and Guowu Yang and Lei Feng and Yufeng Yu and Lixin Duan},
  title = {{Learning cross-domain semantic-visual relationships for transductive zero-shot learning}},
  journal = {Pattern Recognition},
  year = {2023},
  url = {https://openreview.net/forum?id=S4WwvRnFgN},
}
Figure