Correlation-Guided Distribution and Geometry Alignments for Heterogeneous Domain Adaptation

Wai Keung Wong, Dewei Lin, Yuwu Lu, Jiajun Wen, Zhihui Lai, Xuelong Li

Abstract

In this paper, we present a novel approach named correlation-guided distribution and geometry alignments (CDGA) for heterogeneous domain adaptation. Unlike existing methods that typically combine feature alignment and domain alignment into a single objective function, our proposed CDGA separates the two alignments into distinct steps. The two adaptation steps are: paired canonical correlation analysis (PCCA) and distribution and geometry alignments (DGA). In the PCCA step, CDGA focuses on maximizing the within-category correlation between source and target samples to produce the dimension-aligned feature representations for the next adaptation step. In the DGA step, CDGA is responsible for learning a classifier that incorporates both distribution and geometry alignments. Furthermore, during this step, the highly confident pseudo labeled samples are carefully selected for the next iteration of PCCA, establishing a beneficial coupling between PCCA and DGA to improve the adaptation performance in an iterative manner. Experimental results on various visual cross-domain benchmarks demonstrate that CDGA achieves remarkable performance compared to the existing shallow heterogeneous domain adaptation methods and even exhibits superiority over the state-of-the-art neural network-based approaches.
BibTeX
@article{wong2024correlation,
  author = {Wai Keung Wong and Dewei Lin and Yuwu Lu and Jiajun Wen and Zhihui Lai and Xuelong Li},
  title = {{Correlation-Guided Distribution and Geometry Alignments for Heterogeneous Domain Adaptation}},
  journal = {IEEE Trans. Multimedia},
  year = {2024},
  url = {https://openreview.net/forum?id=USp56l1Peq},
}

Loading related content...

Figure