Exploiting Local Feature Patterns for Unsupervised Domain Adaptation


  • Jun Wen Zhejiang University
  • Risheng Liu Dalian University of Technology
  • Nenggan Zheng Zhejiang University
  • Qian Zheng Zhejiang University
  • Zhefeng Gong Zhejiang University
  • Junsong Yuan State University of New York at Buffalo




Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local features and their multi-mode statistics. We show that the learned local feature patterns are more generic and transferable and a further local feature distribution matching enables fine-grained feature alignment. In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics. Comparisons to the state-of-the-art unsupervised domain adaptation methods on two popular benchmark datasets demonstrate the superiority of our approach and its effectiveness on alleviating negative transfer.




How to Cite

Wen, J., Liu, R., Zheng, N., Zheng, Q., Gong, Z., & Yuan, J. (2019). Exploiting Local Feature Patterns for Unsupervised Domain Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 5401-5408. https://doi.org/10.1609/aaai.v33i01.33015401



AAAI Technical Track: Machine Learning