HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation

By Chao Chen, Zhihang Fu, Zhihong Chen, Sheng Jin, Zhaowei Cheng, Xinyu Jin, Xiansheng Hua. 2019

262 citations recorded by the source corpus.

Minimizing the discrepancy of feature distributions between different domains is one of the most promising directions in unsupervised domain adaptation. From the perspective of moment matching, most existing discrepancy-based methods are designed to match the second-order or lower moments, which however, have limited expression of statistical characteristic for non-Gaussian distributions. In this work, we propose a Higher-order Moment Matching (HoMM) method, and further extend the HoMM into reproducing kernel Hilbert spaces (RKHS). In particular, our proposed HoMM can perform arbitrary-order moment matching, we show that the first-order HoMM is equivalent to Maximum Mean Discrepancy (MMD) and the second-order HoMM is equivalent to Correlation Alignment (CORAL). Moreover, HoMM (order≥ 3) is expected to perform fine-grained domain alignment as higher-order statistics can approximate more complex, non-Gaussian distributions. Besides, we also exploit the pseudo-labeled target samples to learn discriminative representations in the target domain, which further improves the transfer performance. Extensive experiments are conducted, showing that our proposed HoMM consistently outperforms the existing moment matching methods by a large margin. Codes are available at https://github.com/chenchao666/HoMM-Master

Subfields: Artificial Intelligence, Cancer Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. B. V. Delft
  2. Diane Joyce Cook
  3. Yuejiang Liu
  4. Taylor Mordan
  5. Baptiste Bellot-Gurlet
  6. Garrett Wilson
  7. Alexandre Alahi
  8. Parth Kothari

In Cancer Research

  1. Diane Joyce Cook
  2. Garrett Wilson

Citations in the corpus